
#Importing the libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.offline as py
import plotly.offline as offline
import plotly.graph_objects as go
import cufflinks as cf
cf.go_offline()
from plotly.offline import init_notebook_mode, iplot
import warnings
warnings.filterwarnings('ignore')
pd.reset_option('display.max_columns',None)


#loading the data
app_train=pd.read_csv('application_train.csv') #current applications
pos_bal = pd.read_csv('POS_CASH_balance.csv')   #previous applications to check if anyone has applied before
bure_bal = pd.read_csv('bureau_balance.csv')
prev_app = pd.read_csv('previous_application.csv')
inst_pay = pd.read_csv('installments_payments.csv')
cred_bal = pd.read_csv('credit_card_balance.csv')
bure = pd.read_csv('bureau.csv')


# Checking the dimension of our dataset
print(app_train.shape)
print(pos_bal.shape)
print(bure_bal.shape)
print(prev_app.shape)
print(inst_pay.shape)
print(cred_bal.shape)
print(bure.shape)

(307511, 122)
(10001358, 8)
(27299925, 3)
(1670214, 37)
(13605401, 8)
(3840312, 23)
(1716428, 17)


app_train.head()#Getting the first five rows


app_train.columns.values

array(['SK_ID_CURR', 'TARGET', 'NAME_CONTRACT_TYPE', 'CODE_GENDER',
       'FLAG_OWN_CAR', 'FLAG_OWN_REALTY', 'CNT_CHILDREN',
       'AMT_INCOME_TOTAL', 'AMT_CREDIT', 'AMT_ANNUITY', 'AMT_GOODS_PRICE',
       'NAME_TYPE_SUITE', 'NAME_INCOME_TYPE', 'NAME_EDUCATION_TYPE',
       'NAME_FAMILY_STATUS', 'NAME_HOUSING_TYPE',
       'REGION_POPULATION_RELATIVE', 'DAYS_BIRTH', 'DAYS_EMPLOYED',
       'DAYS_REGISTRATION', 'DAYS_ID_PUBLISH', 'OWN_CAR_AGE',
       'FLAG_MOBIL', 'FLAG_EMP_PHONE', 'FLAG_WORK_PHONE',
       'FLAG_CONT_MOBILE', 'FLAG_PHONE', 'FLAG_EMAIL', 'OCCUPATION_TYPE',
       'CNT_FAM_MEMBERS', 'REGION_RATING_CLIENT',
       'REGION_RATING_CLIENT_W_CITY', 'WEEKDAY_APPR_PROCESS_START',
       'HOUR_APPR_PROCESS_START', 'REG_REGION_NOT_LIVE_REGION',
       'REG_REGION_NOT_WORK_REGION', 'LIVE_REGION_NOT_WORK_REGION',
       'REG_CITY_NOT_LIVE_CITY', 'REG_CITY_NOT_WORK_CITY',
       'LIVE_CITY_NOT_WORK_CITY', 'ORGANIZATION_TYPE', 'EXT_SOURCE_1',
       'EXT_SOURCE_2', 'EXT_SOURCE_3', 'APARTMENTS_AVG',
       'BASEMENTAREA_AVG', 'YEARS_BEGINEXPLUATATION_AVG',
       'YEARS_BUILD_AVG', 'COMMONAREA_AVG', 'ELEVATORS_AVG',
       'ENTRANCES_AVG', 'FLOORSMAX_AVG', 'FLOORSMIN_AVG', 'LANDAREA_AVG',
       'LIVINGAPARTMENTS_AVG', 'LIVINGAREA_AVG',
       'NONLIVINGAPARTMENTS_AVG', 'NONLIVINGAREA_AVG', 'APARTMENTS_MODE',
       'BASEMENTAREA_MODE', 'YEARS_BEGINEXPLUATATION_MODE',
       'YEARS_BUILD_MODE', 'COMMONAREA_MODE', 'ELEVATORS_MODE',
       'ENTRANCES_MODE', 'FLOORSMAX_MODE', 'FLOORSMIN_MODE',
       'LANDAREA_MODE', 'LIVINGAPARTMENTS_MODE', 'LIVINGAREA_MODE',
       'NONLIVINGAPARTMENTS_MODE', 'NONLIVINGAREA_MODE',
       'APARTMENTS_MEDI', 'BASEMENTAREA_MEDI',
       'YEARS_BEGINEXPLUATATION_MEDI', 'YEARS_BUILD_MEDI',
       'COMMONAREA_MEDI', 'ELEVATORS_MEDI', 'ENTRANCES_MEDI',
       'FLOORSMAX_MEDI', 'FLOORSMIN_MEDI', 'LANDAREA_MEDI',
       'LIVINGAPARTMENTS_MEDI', 'LIVINGAREA_MEDI',
       'NONLIVINGAPARTMENTS_MEDI', 'NONLIVINGAREA_MEDI',
       'FONDKAPREMONT_MODE', 'HOUSETYPE_MODE', 'TOTALAREA_MODE',
       'WALLSMATERIAL_MODE', 'EMERGENCYSTATE_MODE',
       'OBS_30_CNT_SOCIAL_CIRCLE', 'DEF_30_CNT_SOCIAL_CIRCLE',
       'OBS_60_CNT_SOCIAL_CIRCLE', 'DEF_60_CNT_SOCIAL_CIRCLE',
       'DAYS_LAST_PHONE_CHANGE', 'FLAG_DOCUMENT_2', 'FLAG_DOCUMENT_3',
       'FLAG_DOCUMENT_4', 'FLAG_DOCUMENT_5', 'FLAG_DOCUMENT_6',
       'FLAG_DOCUMENT_7', 'FLAG_DOCUMENT_8', 'FLAG_DOCUMENT_9',
       'FLAG_DOCUMENT_10', 'FLAG_DOCUMENT_11', 'FLAG_DOCUMENT_12',
       'FLAG_DOCUMENT_13', 'FLAG_DOCUMENT_14', 'FLAG_DOCUMENT_15',
       'FLAG_DOCUMENT_16', 'FLAG_DOCUMENT_17', 'FLAG_DOCUMENT_18',
       'FLAG_DOCUMENT_19', 'FLAG_DOCUMENT_20', 'FLAG_DOCUMENT_21',
       'AMT_REQ_CREDIT_BUREAU_HOUR', 'AMT_REQ_CREDIT_BUREAU_DAY',
       'AMT_REQ_CREDIT_BUREAU_WEEK', 'AMT_REQ_CREDIT_BUREAU_MON',
       'AMT_REQ_CREDIT_BUREAU_QRT', 'AMT_REQ_CREDIT_BUREAU_YEAR'],
      dtype=object)


app_train.describe()#Used to view some basic statistical details like percentile,mean,std etc


app_train.info()#To check data type and null values for all columns

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 307511 entries, 0 to 307510
Columns: 122 entries, SK_ID_CURR to AMT_REQ_CREDIT_BUREAU_YEAR
dtypes: float64(65), int64(41), object(16)
memory usage: 286.2+ MB


pos_bal.head()#Getting the first five rows


pos_bal.columns.values

array(['SK_ID_PREV', 'SK_ID_CURR', 'MONTHS_BALANCE', 'CNT_INSTALMENT',
       'CNT_INSTALMENT_FUTURE', 'NAME_CONTRACT_STATUS', 'SK_DPD',
       'SK_DPD_DEF'], dtype=object)


pos_bal.describe()#Used to view some basic statistical details like percentile,mean,std etc.


pos_bal.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10001358 entries, 0 to 10001357
Data columns (total 8 columns):
 #   Column                 Dtype  
---  ------                 -----  
 0   SK_ID_PREV             int64  
 1   SK_ID_CURR             int64  
 2   MONTHS_BALANCE         int64  
 3   CNT_INSTALMENT         float64
 4   CNT_INSTALMENT_FUTURE  float64
 5   NAME_CONTRACT_STATUS   object 
 6   SK_DPD                 int64  
 7   SK_DPD_DEF             int64  
dtypes: float64(2), int64(5), object(1)
memory usage: 610.4+ MB


bure_bal.head()#Getting the first five rows


bure_bal.columns.values

array(['SK_ID_BUREAU', 'MONTHS_BALANCE', 'STATUS'], dtype=object)


bure_bal.describe()#Used to view some basic statistical details like percentile,mean,std etc.


bure_bal.info()#To check data type and null values for all columns

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 27299925 entries, 0 to 27299924
Data columns (total 3 columns):
 #   Column          Dtype 
---  ------          ----- 
 0   SK_ID_BUREAU    int64 
 1   MONTHS_BALANCE  int64 
 2   STATUS          object
dtypes: int64(2), object(1)
memory usage: 624.8+ MB


prev_app.head()#Getting the first five rows


prev_app.columns.values

array(['SK_ID_PREV', 'SK_ID_CURR', 'NAME_CONTRACT_TYPE', 'AMT_ANNUITY',
       'AMT_APPLICATION', 'AMT_CREDIT', 'AMT_DOWN_PAYMENT',
       'AMT_GOODS_PRICE', 'WEEKDAY_APPR_PROCESS_START',
       'HOUR_APPR_PROCESS_START', 'FLAG_LAST_APPL_PER_CONTRACT',
       'NFLAG_LAST_APPL_IN_DAY', 'RATE_DOWN_PAYMENT',
       'RATE_INTEREST_PRIMARY', 'RATE_INTEREST_PRIVILEGED',
       'NAME_CASH_LOAN_PURPOSE', 'NAME_CONTRACT_STATUS', 'DAYS_DECISION',
       'NAME_PAYMENT_TYPE', 'CODE_REJECT_REASON', 'NAME_TYPE_SUITE',
       'NAME_CLIENT_TYPE', 'NAME_GOODS_CATEGORY', 'NAME_PORTFOLIO',
       'NAME_PRODUCT_TYPE', 'CHANNEL_TYPE', 'SELLERPLACE_AREA',
       'NAME_SELLER_INDUSTRY', 'CNT_PAYMENT', 'NAME_YIELD_GROUP',
       'PRODUCT_COMBINATION', 'DAYS_FIRST_DRAWING', 'DAYS_FIRST_DUE',
       'DAYS_LAST_DUE_1ST_VERSION', 'DAYS_LAST_DUE', 'DAYS_TERMINATION',
       'NFLAG_INSURED_ON_APPROVAL'], dtype=object)


prev_app.describe()#Used to view some basic statistical details like percentile,mean,std etc.


prev_app.info()#To check data type and null values for all columns

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1670214 entries, 0 to 1670213
Data columns (total 37 columns):
 #   Column                       Non-Null Count    Dtype  
---  ------                       --------------    -----  
 0   SK_ID_PREV                   1670214 non-null  int64  
 1   SK_ID_CURR                   1670214 non-null  int64  
 2   NAME_CONTRACT_TYPE           1670214 non-null  object 
 3   AMT_ANNUITY                  1297979 non-null  float64
 4   AMT_APPLICATION              1670214 non-null  float64
 5   AMT_CREDIT                   1670213 non-null  float64
 6   AMT_DOWN_PAYMENT             774370 non-null   float64
 7   AMT_GOODS_PRICE              1284699 non-null  float64
 8   WEEKDAY_APPR_PROCESS_START   1670214 non-null  object 
 9   HOUR_APPR_PROCESS_START      1670214 non-null  int64  
 10  FLAG_LAST_APPL_PER_CONTRACT  1670214 non-null  object 
 11  NFLAG_LAST_APPL_IN_DAY       1670214 non-null  int64  
 12  RATE_DOWN_PAYMENT            774370 non-null   float64
 13  RATE_INTEREST_PRIMARY        5951 non-null     float64
 14  RATE_INTEREST_PRIVILEGED     5951 non-null     float64
 15  NAME_CASH_LOAN_PURPOSE       1670214 non-null  object 
 16  NAME_CONTRACT_STATUS         1670214 non-null  object 
 17  DAYS_DECISION                1670214 non-null  int64  
 18  NAME_PAYMENT_TYPE            1670214 non-null  object 
 19  CODE_REJECT_REASON           1670214 non-null  object 
 20  NAME_TYPE_SUITE              849809 non-null   object 
 21  NAME_CLIENT_TYPE             1670214 non-null  object 
 22  NAME_GOODS_CATEGORY          1670214 non-null  object 
 23  NAME_PORTFOLIO               1670214 non-null  object 
 24  NAME_PRODUCT_TYPE            1670214 non-null  object 
 25  CHANNEL_TYPE                 1670214 non-null  object 
 26  SELLERPLACE_AREA             1670214 non-null  int64  
 27  NAME_SELLER_INDUSTRY         1670214 non-null  object 
 28  CNT_PAYMENT                  1297984 non-null  float64
 29  NAME_YIELD_GROUP             1670214 non-null  object 
 30  PRODUCT_COMBINATION          1669868 non-null  object 
 31  DAYS_FIRST_DRAWING           997149 non-null   float64
 32  DAYS_FIRST_DUE               997149 non-null   float64
 33  DAYS_LAST_DUE_1ST_VERSION    997149 non-null   float64
 34  DAYS_LAST_DUE                997149 non-null   float64
 35  DAYS_TERMINATION             997149 non-null   float64
 36  NFLAG_INSURED_ON_APPROVAL    997149 non-null   float64
dtypes: float64(15), int64(6), object(16)
memory usage: 471.5+ MB


cred_bal.head()


cred_bal.columns.values

array(['SK_ID_PREV', 'SK_ID_CURR', 'MONTHS_BALANCE', 'AMT_BALANCE',
       'AMT_CREDIT_LIMIT_ACTUAL', 'AMT_DRAWINGS_ATM_CURRENT',
       'AMT_DRAWINGS_CURRENT', 'AMT_DRAWINGS_OTHER_CURRENT',
       'AMT_DRAWINGS_POS_CURRENT', 'AMT_INST_MIN_REGULARITY',
       'AMT_PAYMENT_CURRENT', 'AMT_PAYMENT_TOTAL_CURRENT',
       'AMT_RECEIVABLE_PRINCIPAL', 'AMT_RECIVABLE',
       'AMT_TOTAL_RECEIVABLE', 'CNT_DRAWINGS_ATM_CURRENT',
       'CNT_DRAWINGS_CURRENT', 'CNT_DRAWINGS_OTHER_CURRENT',
       'CNT_DRAWINGS_POS_CURRENT', 'CNT_INSTALMENT_MATURE_CUM',
       'NAME_CONTRACT_STATUS', 'SK_DPD', 'SK_DPD_DEF'], dtype=object)


cred_bal.describe()#Used to view some basic statistical details like percentile,mean,std etc.


cred_bal.info()#To check data type and null values for all columns

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3840312 entries, 0 to 3840311
Data columns (total 23 columns):
 #   Column                      Dtype  
---  ------                      -----  
 0   SK_ID_PREV                  int64  
 1   SK_ID_CURR                  int64  
 2   MONTHS_BALANCE              int64  
 3   AMT_BALANCE                 float64
 4   AMT_CREDIT_LIMIT_ACTUAL     int64  
 5   AMT_DRAWINGS_ATM_CURRENT    float64
 6   AMT_DRAWINGS_CURRENT        float64
 7   AMT_DRAWINGS_OTHER_CURRENT  float64
 8   AMT_DRAWINGS_POS_CURRENT    float64
 9   AMT_INST_MIN_REGULARITY     float64
 10  AMT_PAYMENT_CURRENT         float64
 11  AMT_PAYMENT_TOTAL_CURRENT   float64
 12  AMT_RECEIVABLE_PRINCIPAL    float64
 13  AMT_RECIVABLE               float64
 14  AMT_TOTAL_RECEIVABLE        float64
 15  CNT_DRAWINGS_ATM_CURRENT    float64
 16  CNT_DRAWINGS_CURRENT        int64  
 17  CNT_DRAWINGS_OTHER_CURRENT  float64
 18  CNT_DRAWINGS_POS_CURRENT    float64
 19  CNT_INSTALMENT_MATURE_CUM   float64
 20  NAME_CONTRACT_STATUS        object 
 21  SK_DPD                      int64  
 22  SK_DPD_DEF                  int64  
dtypes: float64(15), int64(7), object(1)
memory usage: 673.9+ MB


bure.head()#Getting the first five rows


bure.columns.values

array(['SK_ID_CURR', 'SK_ID_BUREAU', 'CREDIT_ACTIVE', 'CREDIT_CURRENCY',
       'DAYS_CREDIT', 'CREDIT_DAY_OVERDUE', 'DAYS_CREDIT_ENDDATE',
       'DAYS_ENDDATE_FACT', 'AMT_CREDIT_MAX_OVERDUE',
       'CNT_CREDIT_PROLONG', 'AMT_CREDIT_SUM', 'AMT_CREDIT_SUM_DEBT',
       'AMT_CREDIT_SUM_LIMIT', 'AMT_CREDIT_SUM_OVERDUE', 'CREDIT_TYPE',
       'DAYS_CREDIT_UPDATE', 'AMT_ANNUITY'], dtype=object)


bure.describe()#Used to view some basic statistical details like percentile,mean,std etc.


bure.info()#To check data type and null values for all columns

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1716428 entries, 0 to 1716427
Data columns (total 17 columns):
 #   Column                  Dtype  
---  ------                  -----  
 0   SK_ID_CURR              int64  
 1   SK_ID_BUREAU            int64  
 2   CREDIT_ACTIVE           object 
 3   CREDIT_CURRENCY         object 
 4   DAYS_CREDIT             int64  
 5   CREDIT_DAY_OVERDUE      int64  
 6   DAYS_CREDIT_ENDDATE     float64
 7   DAYS_ENDDATE_FACT       float64
 8   AMT_CREDIT_MAX_OVERDUE  float64
 9   CNT_CREDIT_PROLONG      int64  
 10  AMT_CREDIT_SUM          float64
 11  AMT_CREDIT_SUM_DEBT     float64
 12  AMT_CREDIT_SUM_LIMIT    float64
 13  AMT_CREDIT_SUM_OVERDUE  float64
 14  CREDIT_TYPE             object 
 15  DAYS_CREDIT_UPDATE      int64  
 16  AMT_ANNUITY             float64
dtypes: float64(8), int64(6), object(3)
memory usage: 222.6+ MB


# checking missing data
total = app_train.isnull().sum().sort_values(ascending = False)
percent = (app_train.isnull().sum()/app_train.isnull().count()*100).sort_values(ascending = False)
missing_app_train_data  = pd.concat([total, percent], axis=1, keys=['Total', 'Percent'])
missing_app_train_data.head(20)


# checking missing data
total = pos_bal.isnull().sum().sort_values(ascending = False)
percent = (pos_bal.isnull().sum()/pos_bal.isnull().count()*100).sort_values(ascending = False)
missing_pos_bal_data  = pd.concat([total, percent], axis=1, keys=['Total', 'Percent'])
missing_pos_bal_data.head(3)


# checking missing data
total = bure_bal.isnull().sum().sort_values(ascending = False)
percent = (bure_bal.isnull().sum()/bure_bal.isnull().count()*100).sort_values(ascending = False)
missing_bure_bal_data  = pd.concat([total, percent], axis=1, keys=['Total', 'Percent'])
missing_bure_bal_data.head(3)


# checking missing data
total = prev_app.isnull().sum().sort_values(ascending = False)
percent = (prev_app.isnull().sum()/prev_app.isnull().count()*100).sort_values(ascending = False)
missing_prev_app_data  = pd.concat([total, percent], axis=1, keys=['Total', 'Percent'])
missing_prev_app_data.head(20)


# checking missing data
total = inst_pay.isnull().sum().sort_values(ascending = False)
percent = (inst_pay.isnull().sum()/inst_pay.isnull().count()*100).sort_values(ascending = False)
missing_inst_pay_data  = pd.concat([total, percent], axis=1, keys=['Total', 'Percent'])
missing_inst_pay_data.head(3)


# checking missing data
total = cred_bal.isnull().sum().sort_values(ascending = False)
percent = (cred_bal.isnull().sum()/cred_bal.isnull().count()*100).sort_values(ascending = False)
missing_cred_bal_data  = pd.concat([total, percent], axis=1, keys=['Total', 'Percent'])
missing_cred_bal_data.head(10)


# checking missing data
total = bure.isnull().sum().sort_values(ascending = False)
percent = (bure.isnull().sum()/bure.isnull().count()*100).sort_values(ascending = False)
missing_bure_data  = pd.concat([total, percent], axis=1, keys=['Total', 'Percent'])
missing_bure_data.head(8)


# Distribution of AMT_CREDI
cf.go_offline()

app_train['AMT_CREDIT'].iplot(kind='histogram', bins=100, xTitle='Credit Amount',
                              yTitle='Count of applicants', title='Distribution of AMT_CREDIT')


cf.set_config_file(theme='pearl')
(app_train['DAYS_EMPLOYED']).iplot(kind='histogram', 
             xTitle = 'Days',bins=50,
             yTitle='Count of applicants in %',
             title='Days before the application the person started current employment')


#Distribution of AMT_INCOME_TOTAL
app_train[app_train['AMT_INCOME_TOTAL'] < 2000000]['AMT_INCOME_TOTAL'].iplot(kind='histogram', bins=100,
   xTitle = 'Total Income', yTitle ='Count of applicants',
             title='Distribution of AMT_INCOME_TOTAL')


# Who accompanied client when applying for the application
cf.set_config_file(theme='polar')
suite_val = (app_train['NAME_TYPE_SUITE'].value_counts()/len(app_train))*100
suite_val.iplot(kind='bar', xTitle = 'Name of type of the Suite',
             yTitle='Count of applicants in %',
             title='Who accompanied client when applying for the  application in % ')


suite_val = app_train['NAME_TYPE_SUITE'].value_counts()

suite_val_y0 = app_train.loc[app_train['TARGET'] == 0, 'NAME_TYPE_SUITE'].value_counts()
suite_val_y1 = app_train.loc[app_train['TARGET'] == 1, 'NAME_TYPE_SUITE'].value_counts()

data = [
    go.Bar(x=suite_val.index, y=(suite_val_y1 / suite_val.sum()) * 100, name='Yes'),
    go.Bar(x=suite_val.index, y=(suite_val_y0 / suite_val.sum()) * 100, name='No')
]

layout = go.Layout(
    title="Who accompanied the client when applying for the loan in terms of loan repayment status (%)",
    xaxis=dict(title='Name of the type of Suite'),
    yaxis=dict(title='Count of applicants (%)')
)

fig = go.Figure(data=data, layout=layout)
fig.layout.template = 'plotly_dark'
fig.show()


income_val = app_train['NAME_INCOME_TYPE'].value_counts()
income_val_y0 = []
income_val_y1 = []
for val in income_val.index:
    income_val_y1.append(np.sum(app_train['TARGET'][app_train['NAME_INCOME_TYPE']==val] == 1))
    income_val_y0.append(np.sum(app_train['TARGET'][app_train['NAME_INCOME_TYPE']==val] == 0))
data = [go.Bar(x = income_val.index, y = ((income_val_y1 / income_val.sum()) * 100), name='Yes' ),
        go.Bar(x = income_val.index, y = ((income_val_y0 / income_val.sum()) * 100), name='No' )]
layout = go.Layout(
    title = "Income sources of Applicants in terms of loan is repayed or not  in %",
    xaxis=dict(
        title='Income source',
       ),
    yaxis=dict(
        title='Count of applicants in %',
        )
)
fig = go.Figure(data = data, layout=layout)
fig.layout.template = 'plotly_dark'
py.iplot(fig)


education_val = app_train['NAME_EDUCATION_TYPE'].value_counts()
education_val_y0 = []
education_val_y1 = []
for val in education_val.index:
    education_val_y1.append(np.sum(app_train['TARGET'][app_train['NAME_EDUCATION_TYPE']==val] == 1))
    education_val_y0.append(np.sum(app_train['TARGET'][app_train['NAME_EDUCATION_TYPE']==val] == 0))
data = [go.Bar(x = education_val.index, y = ((education_val_y1 / education_val.sum()) * 100), name='Yes' ),
        go.Bar(x = education_val.index, y = ((education_val_y0 / education_val.sum()) * 100), name='No' )]
layout = go.Layout(
    title = "Education sources of Applicants in terms of loan is repayed or not  in %",
    xaxis=dict(
        title='Education of Applicants',
       ),
    yaxis=dict(
        title='Count of applicants in %',
        )
)
fig = go.Figure(data = data, layout=layout)
fig.layout.template = 'plotly_dark'
py.iplot(fig)


education_val = app_train['NAME_FAMILY_STATUS'].value_counts()
education_val_y0 = []
education_val_y1 = []
for val in education_val.index:
    education_val_y1.append(np.sum(app_train['TARGET'][app_train['NAME_FAMILY_STATUS']==val] == 1))
    education_val_y0.append(np.sum(app_train['TARGET'][app_train['NAME_FAMILY_STATUS']==val] == 0))
data = [go.Bar(x = education_val.index, y = ((education_val_y1 / education_val.sum()) * 100), name='Yes' ),
        go.Bar(x = education_val.index, y = ((education_val_y0 / education_val.sum()) * 100), name='No' )]
layout = go.Layout(
    title = "Family status of Applicants in terms of loan is repayed or not.%",
    xaxis=dict(
        title='Education of Applicants',
       ),
    yaxis=dict(
        title='Count of applicants in %',
        )
)
fig = go.Figure(data = data, layout=layout)
fig.layout.template = 'plotly_dark'
py.iplot(fig)


temp = app_train["TARGET"].value_counts()
df = pd.DataFrame({'labels': temp.index,
                   'values': temp.values
                  })
df.iplot(kind='pie',labels='labels',values='values', title='Loan Repayed or not')


cf.set_config_file(theme='polar')
contract_val = app_train['NAME_CONTRACT_TYPE'].value_counts()
contract_df = pd.DataFrame({'labels': contract_val.index,
                   'values': contract_val.values
                  })
contract_df.iplot(kind='pie',labels='labels',values='values', title='Types of Loan', hole = 0.6)


temp = app_train["NAME_FAMILY_STATUS"].value_counts()
df = pd.DataFrame({'labels': temp.index,
                   'values': temp.values
                  })
df.iplot(kind='pie',labels='labels',values='values', title='Family Status of Applicant\'s', hole = 0.5)


temp = app_train["NAME_INCOME_TYPE"].value_counts()
df = pd.DataFrame({'labels': temp.index,
                   'values': temp.values
                  })
df.iplot(kind='pie',labels='labels',values='values', title='Income sources of Applicant\'s', hole = 0.5)


temp = app_train["NAME_EDUCATION_TYPE"].value_counts()
df = pd.DataFrame({'labels': temp.index,
                   'values': temp.values
                  })
df.iplot(kind='pie',labels='labels',values='values', title='Education of Applicant\'s', hole = 0.5)


temp = app_train["NAME_HOUSING_TYPE"].value_counts()
df = pd.DataFrame({'labels': temp.index,
                   'values': temp.values
                  })
df.iplot(kind='pie',labels='labels',values='values', title='Type of House', hole = 0.5)


temp = app_train["OCCUPATION_TYPE"].value_counts()
temp.iplot(kind='bar', xTitle = 'Occupation', yTitle = "Count", title = 'Occupation of Applicant\'s who applied for loan', color = 'green')


temp = app_train["ORGANIZATION_TYPE"].value_counts()
temp.iplot(kind='bar', xTitle = 'Organization Name', yTitle = "Count", title = 'Types of Organizations who applied for loan ', color = 'red')


temp = prev_app["NAME_CONTRACT_STATUS"].value_counts()
df = pd.DataFrame({'labels': temp.index,
                   'values': temp.values
                  })
df.iplot(kind='pie',labels='labels',values='values', title='Contract approved or not', hole = 0.5)


temp = prev_app["NAME_PAYMENT_TYPE"].value_counts()
df = pd.DataFrame({'labels': temp.index,
                   'values': temp.values
                  })
df.iplot(kind='pie',labels='labels',values='values', title='Payment method that client choose to pay for the previous application', hole = 0.7,colors=['#75e575', '#ea7c96',])


# Flag to represent when Total income is greater than Credit
app_train['INCOME_GT_CREDIT_FLAG'] = app_train['AMT_INCOME_TOTAL'] > app_train['AMT_CREDIT']
# Column to represent Credit Income Percent
app_train['CREDIT_INCOME_PERCENT'] = app_train['AMT_CREDIT'] / app_train['AMT_INCOME_TOTAL']
# Column to represent Annuity Income percent
app_train['ANNUITY_INCOME_PERCENT'] = app_train['AMT_ANNUITY'] / app_train['AMT_INCOME_TOTAL']
# Column to represent Credit Term
app_train['CREDIT_TERM'] = app_train['AMT_CREDIT'] / app_train['AMT_ANNUITY']
# Column to represent Days Employed percent in his life
app_train['DAYS_EMPLOYED_PERCENT'] = app_train['DAYS_EMPLOYED'] / app_train['DAYS_BIRTH']
# Shape of Application data
print('The shape of application data :',app_train.shape)

The shape of application data : (307511, 127)


# Combining numerical features
grp = bure.drop(['SK_ID_BUREAU'], axis = 1).groupby(by=['SK_ID_CURR']).mean().reset_index()
grp.columns = ['BUREAU_'+column if column !='SK_ID_CURR' else column for column in grp.columns]
app_bure = app_train.merge(grp, on='SK_ID_CURR', how='left')
app_bure.update(app_bure[grp.columns].fillna(0))

# Combining categorical features
bure_cat = pd.get_dummies(bure.select_dtypes('object'))
bure_cat['SK_ID_CURR'] = bure['SK_ID_CURR']
grp = bure_cat.groupby(by = ['SK_ID_CURR']).mean().reset_index()
grp.columns = ['BUREAU_'+column if column !='SK_ID_CURR' else column for column in grp.columns]
app_bure = app_bure.merge(grp, on='SK_ID_CURR', how='left')
app_bure.update(app_bure[grp.columns].fillna(0))

# Shape of application and bureau data combined
print('The shape application and bureau data combined:',app_bure.shape)

The shape application and bureau data combined: (307511, 162)


# Number of previous applications per customer
grp = prev_app[['SK_ID_CURR','SK_ID_PREV']].groupby(by=['SK_ID_CURR'])['SK_ID_PREV'].count().reset_index().rename(columns={'SK_ID_PREV':'PREV_APP_COUNT'})
app_bure_prev = app_bure.merge(grp, on =['SK_ID_CURR'], how = 'left')
app_bure_prev['PREV_APP_COUNT'] = app_bure_prev['PREV_APP_COUNT'].fillna(0)

# Combining numerical features
grp = prev_app.drop('SK_ID_PREV', axis =1).groupby(by=['SK_ID_CURR']).mean().reset_index()
prev_columns = ['PREV_'+column if column != 'SK_ID_CURR' else column for column in grp.columns ]
grp.columns = prev_columns
app_bure_prev = app_bure_prev.merge(grp, on =['SK_ID_CURR'], how = 'left')
app_bure_prev.update(app_bure_prev[grp.columns].fillna(0))

# Combining categorical features
prev_cat = pd.get_dummies(prev_app.select_dtypes('object'))
prev_cat['SK_ID_CURR'] = prev_app['SK_ID_CURR']
prev_cat.head()
grp = prev_cat.groupby('SK_ID_CURR').mean().reset_index()
grp.columns = ['PREV_'+column if column != 'SK_ID_CURR' else column for column in grp.columns]
app_bure_prev = app_bure_prev.merge(grp, on=['SK_ID_CURR'], how='left')
app_bure_prev.update(app_bure_prev[grp.columns].fillna(0))


# Combining numerical features
grp = pos_bal.drop('SK_ID_PREV', axis =1).groupby(by=['SK_ID_CURR']).mean().reset_index()
prev_columns = ['POS_'+column if column != 'SK_ID_CURR' else column for column in grp.columns ]
grp.columns = prev_columns
app_bure_prev = app_bure_prev.merge(grp, on =['SK_ID_CURR'], how = 'left')
app_bure_prev.update(app_bure_prev[grp.columns].fillna(0))

# Combining categorical features
pos_bal_cat = pd.get_dummies(pos_bal.select_dtypes('object'))
pos_bal_cat['SK_ID_CURR'] = pos_bal['SK_ID_CURR']
grp = pos_bal_cat.groupby('SK_ID_CURR').mean().reset_index()
grp.columns = ['POS_'+column if column != 'SK_ID_CURR' else column for column in grp.columns]
app_bure_prev = app_bure_prev.merge(grp, on=['SK_ID_CURR'], how='left')
app_bure_prev.update(app_bure_prev[grp.columns].fillna(0))


# Combining numerical features and there are no categorical features in this dataset
grp = inst_pay.drop('SK_ID_PREV', axis =1).groupby(by=['SK_ID_CURR']).mean().reset_index()
prev_columns = ['INSTA_'+column if column != 'SK_ID_CURR' else column for column in grp.columns ]
grp.columns = prev_columns
app_bure_prev = app_bure_prev.merge(grp, on =['SK_ID_CURR'], how = 'left')
app_bure_prev.update(app_bure_prev[grp.columns].fillna(0))


# Combining numerical features
grp = cred_bal.drop('SK_ID_PREV', axis =1).groupby(by=['SK_ID_CURR']).mean().reset_index()
prev_columns = ['CREDIT_'+column if column != 'SK_ID_CURR' else column for column in grp.columns ]
grp.columns = prev_columns
app_bure_prev = app_bure_prev.merge(grp, on =['SK_ID_CURR'], how = 'left')
app_bure_prev.update(app_bure_prev[grp.columns].fillna(0))

# Combining categorical features
cred_cat = pd.get_dummies(cred_bal.select_dtypes('object'))
cred_cat['SK_ID_CURR'] = cred_bal['SK_ID_CURR']
grp = cred_cat.groupby('SK_ID_CURR').mean().reset_index()
grp.columns = ['CREDIT_'+column if column != 'SK_ID_CURR' else column for column in grp.columns]
app_bure_prev = app_bure_prev.merge(grp, on=['SK_ID_CURR'], how='left')
app_bure_prev.update(app_bure_prev[grp.columns].fillna(0))


app_bure_prev


app_bure_prev.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 307511 entries, 0 to 307510
Columns: 372 entries, SK_ID_CURR to CREDIT_NAME_CONTRACT_STATUS_Signed
dtypes: bool(1), float64(314), int64(41), object(16)
memory usage: 873.1+ MB


for col in app_bure_prev.columns:
    print(col,app_bure_prev[col].isnull().sum())

SK_ID_CURR 0
TARGET 0
NAME_CONTRACT_TYPE 0
CODE_GENDER 0
FLAG_OWN_CAR 0
FLAG_OWN_REALTY 0
CNT_CHILDREN 0
AMT_INCOME_TOTAL 0
AMT_CREDIT 0
AMT_ANNUITY 12
AMT_GOODS_PRICE 278
NAME_TYPE_SUITE 1292
NAME_INCOME_TYPE 0
NAME_EDUCATION_TYPE 0
NAME_FAMILY_STATUS 0
NAME_HOUSING_TYPE 0
REGION_POPULATION_RELATIVE 0
DAYS_BIRTH 0
DAYS_EMPLOYED 0
DAYS_REGISTRATION 0
DAYS_ID_PUBLISH 0
OWN_CAR_AGE 202929
FLAG_MOBIL 0
FLAG_EMP_PHONE 0
FLAG_WORK_PHONE 0
FLAG_CONT_MOBILE 0
FLAG_PHONE 0
FLAG_EMAIL 0
OCCUPATION_TYPE 96391
CNT_FAM_MEMBERS 2
REGION_RATING_CLIENT 0
REGION_RATING_CLIENT_W_CITY 0
WEEKDAY_APPR_PROCESS_START 0
HOUR_APPR_PROCESS_START 0
REG_REGION_NOT_LIVE_REGION 0
REG_REGION_NOT_WORK_REGION 0
LIVE_REGION_NOT_WORK_REGION 0
REG_CITY_NOT_LIVE_CITY 0
REG_CITY_NOT_WORK_CITY 0
LIVE_CITY_NOT_WORK_CITY 0
ORGANIZATION_TYPE 0
EXT_SOURCE_1 173378
EXT_SOURCE_2 660
EXT_SOURCE_3 60965
APARTMENTS_AVG 156061
BASEMENTAREA_AVG 179943
YEARS_BEGINEXPLUATATION_AVG 150007
YEARS_BUILD_AVG 204488
COMMONAREA_AVG 214865
ELEVATORS_AVG 163891
ENTRANCES_AVG 154828
FLOORSMAX_AVG 153020
FLOORSMIN_AVG 208642
LANDAREA_AVG 182590
LIVINGAPARTMENTS_AVG 210199
LIVINGAREA_AVG 154350
NONLIVINGAPARTMENTS_AVG 213514
NONLIVINGAREA_AVG 169682
APARTMENTS_MODE 156061
BASEMENTAREA_MODE 179943
YEARS_BEGINEXPLUATATION_MODE 150007
YEARS_BUILD_MODE 204488
COMMONAREA_MODE 214865
ELEVATORS_MODE 163891
ENTRANCES_MODE 154828
FLOORSMAX_MODE 153020
FLOORSMIN_MODE 208642
LANDAREA_MODE 182590
LIVINGAPARTMENTS_MODE 210199
LIVINGAREA_MODE 154350
NONLIVINGAPARTMENTS_MODE 213514
NONLIVINGAREA_MODE 169682
APARTMENTS_MEDI 156061
BASEMENTAREA_MEDI 179943
YEARS_BEGINEXPLUATATION_MEDI 150007
YEARS_BUILD_MEDI 204488
COMMONAREA_MEDI 214865
ELEVATORS_MEDI 163891
ENTRANCES_MEDI 154828
FLOORSMAX_MEDI 153020
FLOORSMIN_MEDI 208642
LANDAREA_MEDI 182590
LIVINGAPARTMENTS_MEDI 210199
LIVINGAREA_MEDI 154350
NONLIVINGAPARTMENTS_MEDI 213514
NONLIVINGAREA_MEDI 169682
FONDKAPREMONT_MODE 210295
HOUSETYPE_MODE 154297
TOTALAREA_MODE 148431
WALLSMATERIAL_MODE 156341
EMERGENCYSTATE_MODE 145755
OBS_30_CNT_SOCIAL_CIRCLE 1021
DEF_30_CNT_SOCIAL_CIRCLE 1021
OBS_60_CNT_SOCIAL_CIRCLE 1021
DEF_60_CNT_SOCIAL_CIRCLE 1021
DAYS_LAST_PHONE_CHANGE 1
FLAG_DOCUMENT_2 0
FLAG_DOCUMENT_3 0
FLAG_DOCUMENT_4 0
FLAG_DOCUMENT_5 0
FLAG_DOCUMENT_6 0
FLAG_DOCUMENT_7 0
FLAG_DOCUMENT_8 0
FLAG_DOCUMENT_9 0
FLAG_DOCUMENT_10 0
FLAG_DOCUMENT_11 0
FLAG_DOCUMENT_12 0
FLAG_DOCUMENT_13 0
FLAG_DOCUMENT_14 0
FLAG_DOCUMENT_15 0
FLAG_DOCUMENT_16 0
FLAG_DOCUMENT_17 0
FLAG_DOCUMENT_18 0
FLAG_DOCUMENT_19 0
FLAG_DOCUMENT_20 0
FLAG_DOCUMENT_21 0
AMT_REQ_CREDIT_BUREAU_HOUR 41519
AMT_REQ_CREDIT_BUREAU_DAY 41519
AMT_REQ_CREDIT_BUREAU_WEEK 41519
AMT_REQ_CREDIT_BUREAU_MON 41519
AMT_REQ_CREDIT_BUREAU_QRT 41519
AMT_REQ_CREDIT_BUREAU_YEAR 41519
INCOME_GT_CREDIT_FLAG 0
CREDIT_INCOME_PERCENT 0
ANNUITY_INCOME_PERCENT 12
CREDIT_TERM 12
DAYS_EMPLOYED_PERCENT 0
BUREAU_DAYS_CREDIT 0
BUREAU_CREDIT_DAY_OVERDUE 0
BUREAU_DAYS_CREDIT_ENDDATE 0
BUREAU_DAYS_ENDDATE_FACT 0
BUREAU_AMT_CREDIT_MAX_OVERDUE 0
BUREAU_CNT_CREDIT_PROLONG 0
BUREAU_AMT_CREDIT_SUM 0
BUREAU_AMT_CREDIT_SUM_DEBT 0
BUREAU_AMT_CREDIT_SUM_LIMIT 0
BUREAU_AMT_CREDIT_SUM_OVERDUE 0
BUREAU_DAYS_CREDIT_UPDATE 0
BUREAU_AMT_ANNUITY 0
BUREAU_CREDIT_ACTIVE_Active 0
BUREAU_CREDIT_ACTIVE_Bad debt 0
BUREAU_CREDIT_ACTIVE_Closed 0
BUREAU_CREDIT_ACTIVE_Sold 0
BUREAU_CREDIT_CURRENCY_currency 1 0
BUREAU_CREDIT_CURRENCY_currency 2 0
BUREAU_CREDIT_CURRENCY_currency 3 0
BUREAU_CREDIT_CURRENCY_currency 4 0
BUREAU_CREDIT_TYPE_Another type of loan 0
BUREAU_CREDIT_TYPE_Car loan 0
BUREAU_CREDIT_TYPE_Cash loan (non-earmarked) 0
BUREAU_CREDIT_TYPE_Consumer credit 0
BUREAU_CREDIT_TYPE_Credit card 0
BUREAU_CREDIT_TYPE_Interbank credit 0
BUREAU_CREDIT_TYPE_Loan for business development 0
BUREAU_CREDIT_TYPE_Loan for purchase of shares (margin lending) 0
BUREAU_CREDIT_TYPE_Loan for the purchase of equipment 0
BUREAU_CREDIT_TYPE_Loan for working capital replenishment 0
BUREAU_CREDIT_TYPE_Microloan 0
BUREAU_CREDIT_TYPE_Mobile operator loan 0
BUREAU_CREDIT_TYPE_Mortgage 0
BUREAU_CREDIT_TYPE_Real estate loan 0
BUREAU_CREDIT_TYPE_Unknown type of loan 0
PREV_APP_COUNT 0
PREV_AMT_ANNUITY 0
PREV_AMT_APPLICATION 0
PREV_AMT_CREDIT 0
PREV_AMT_DOWN_PAYMENT 0
PREV_AMT_GOODS_PRICE 0
PREV_HOUR_APPR_PROCESS_START 0
PREV_NFLAG_LAST_APPL_IN_DAY 0
PREV_RATE_DOWN_PAYMENT 0
PREV_RATE_INTEREST_PRIMARY 0
PREV_RATE_INTEREST_PRIVILEGED 0
PREV_DAYS_DECISION 0
PREV_SELLERPLACE_AREA 0
PREV_CNT_PAYMENT 0
PREV_DAYS_FIRST_DRAWING 0
PREV_DAYS_FIRST_DUE 0
PREV_DAYS_LAST_DUE_1ST_VERSION 0
PREV_DAYS_LAST_DUE 0
PREV_DAYS_TERMINATION 0
PREV_NFLAG_INSURED_ON_APPROVAL 0
PREV_NAME_CONTRACT_TYPE_Cash loans 0
PREV_NAME_CONTRACT_TYPE_Consumer loans 0
PREV_NAME_CONTRACT_TYPE_Revolving loans 0
PREV_NAME_CONTRACT_TYPE_XNA 0
PREV_WEEKDAY_APPR_PROCESS_START_FRIDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_MONDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_SATURDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_SUNDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_THURSDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_TUESDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_WEDNESDAY 0
PREV_FLAG_LAST_APPL_PER_CONTRACT_N 0
PREV_FLAG_LAST_APPL_PER_CONTRACT_Y 0
PREV_NAME_CASH_LOAN_PURPOSE_Building a house or an annex 0
PREV_NAME_CASH_LOAN_PURPOSE_Business development 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a garage 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a holiday home / land 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a home 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a new car 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a used car 0
PREV_NAME_CASH_LOAN_PURPOSE_Car repairs 0
PREV_NAME_CASH_LOAN_PURPOSE_Education 0
PREV_NAME_CASH_LOAN_PURPOSE_Everyday expenses 0
PREV_NAME_CASH_LOAN_PURPOSE_Furniture 0
PREV_NAME_CASH_LOAN_PURPOSE_Gasification / water supply 0
PREV_NAME_CASH_LOAN_PURPOSE_Hobby 0
PREV_NAME_CASH_LOAN_PURPOSE_Journey 0
PREV_NAME_CASH_LOAN_PURPOSE_Medicine 0
PREV_NAME_CASH_LOAN_PURPOSE_Money for a third person 0
PREV_NAME_CASH_LOAN_PURPOSE_Other 0
PREV_NAME_CASH_LOAN_PURPOSE_Payments on other loans 0
PREV_NAME_CASH_LOAN_PURPOSE_Purchase of electronic equipment 0
PREV_NAME_CASH_LOAN_PURPOSE_Refusal to name the goal 0
PREV_NAME_CASH_LOAN_PURPOSE_Repairs 0
PREV_NAME_CASH_LOAN_PURPOSE_Urgent needs 0
PREV_NAME_CASH_LOAN_PURPOSE_Wedding / gift / holiday 0
PREV_NAME_CASH_LOAN_PURPOSE_XAP 0
PREV_NAME_CASH_LOAN_PURPOSE_XNA 0
PREV_NAME_CONTRACT_STATUS_Approved 0
PREV_NAME_CONTRACT_STATUS_Canceled 0
PREV_NAME_CONTRACT_STATUS_Refused 0
PREV_NAME_CONTRACT_STATUS_Unused offer 0
PREV_NAME_PAYMENT_TYPE_Cash through the bank 0
PREV_NAME_PAYMENT_TYPE_Cashless from the account of the employer 0
PREV_NAME_PAYMENT_TYPE_Non-cash from your account 0
PREV_NAME_PAYMENT_TYPE_XNA 0
PREV_CODE_REJECT_REASON_CLIENT 0
PREV_CODE_REJECT_REASON_HC 0
PREV_CODE_REJECT_REASON_LIMIT 0
PREV_CODE_REJECT_REASON_SCO 0
PREV_CODE_REJECT_REASON_SCOFR 0
PREV_CODE_REJECT_REASON_SYSTEM 0
PREV_CODE_REJECT_REASON_VERIF 0
PREV_CODE_REJECT_REASON_XAP 0
PREV_CODE_REJECT_REASON_XNA 0
PREV_NAME_TYPE_SUITE_Children 0
PREV_NAME_TYPE_SUITE_Family 0
PREV_NAME_TYPE_SUITE_Group of people 0
PREV_NAME_TYPE_SUITE_Other_A 0
PREV_NAME_TYPE_SUITE_Other_B 0
PREV_NAME_TYPE_SUITE_Spouse, partner 0
PREV_NAME_TYPE_SUITE_Unaccompanied 0
PREV_NAME_CLIENT_TYPE_New 0
PREV_NAME_CLIENT_TYPE_Refreshed 0
PREV_NAME_CLIENT_TYPE_Repeater 0
PREV_NAME_CLIENT_TYPE_XNA 0
PREV_NAME_GOODS_CATEGORY_Additional Service 0
PREV_NAME_GOODS_CATEGORY_Animals 0
PREV_NAME_GOODS_CATEGORY_Audio/Video 0
PREV_NAME_GOODS_CATEGORY_Auto Accessories 0
PREV_NAME_GOODS_CATEGORY_Clothing and Accessories 0
PREV_NAME_GOODS_CATEGORY_Computers 0
PREV_NAME_GOODS_CATEGORY_Construction Materials 0
PREV_NAME_GOODS_CATEGORY_Consumer Electronics 0
PREV_NAME_GOODS_CATEGORY_Direct Sales 0
PREV_NAME_GOODS_CATEGORY_Education 0
PREV_NAME_GOODS_CATEGORY_Fitness 0
PREV_NAME_GOODS_CATEGORY_Furniture 0
PREV_NAME_GOODS_CATEGORY_Gardening 0
PREV_NAME_GOODS_CATEGORY_Homewares 0
PREV_NAME_GOODS_CATEGORY_House Construction 0
PREV_NAME_GOODS_CATEGORY_Insurance 0
PREV_NAME_GOODS_CATEGORY_Jewelry 0
PREV_NAME_GOODS_CATEGORY_Medical Supplies 0
PREV_NAME_GOODS_CATEGORY_Medicine 0
PREV_NAME_GOODS_CATEGORY_Mobile 0
PREV_NAME_GOODS_CATEGORY_Office Appliances 0
PREV_NAME_GOODS_CATEGORY_Other 0
PREV_NAME_GOODS_CATEGORY_Photo / Cinema Equipment 0
PREV_NAME_GOODS_CATEGORY_Sport and Leisure 0
PREV_NAME_GOODS_CATEGORY_Tourism 0
PREV_NAME_GOODS_CATEGORY_Vehicles 0
PREV_NAME_GOODS_CATEGORY_Weapon 0
PREV_NAME_GOODS_CATEGORY_XNA 0
PREV_NAME_PORTFOLIO_Cards 0
PREV_NAME_PORTFOLIO_Cars 0
PREV_NAME_PORTFOLIO_Cash 0
PREV_NAME_PORTFOLIO_POS 0
PREV_NAME_PORTFOLIO_XNA 0
PREV_NAME_PRODUCT_TYPE_XNA 0
PREV_NAME_PRODUCT_TYPE_walk-in 0
PREV_NAME_PRODUCT_TYPE_x-sell 0
PREV_CHANNEL_TYPE_AP+ (Cash loan) 0
PREV_CHANNEL_TYPE_Car dealer 0
PREV_CHANNEL_TYPE_Channel of corporate sales 0
PREV_CHANNEL_TYPE_Contact center 0
PREV_CHANNEL_TYPE_Country-wide 0
PREV_CHANNEL_TYPE_Credit and cash offices 0
PREV_CHANNEL_TYPE_Regional / Local 0
PREV_CHANNEL_TYPE_Stone 0
PREV_NAME_SELLER_INDUSTRY_Auto technology 0
PREV_NAME_SELLER_INDUSTRY_Clothing 0
PREV_NAME_SELLER_INDUSTRY_Connectivity 0
PREV_NAME_SELLER_INDUSTRY_Construction 0
PREV_NAME_SELLER_INDUSTRY_Consumer electronics 0
PREV_NAME_SELLER_INDUSTRY_Furniture 0
PREV_NAME_SELLER_INDUSTRY_Industry 0
PREV_NAME_SELLER_INDUSTRY_Jewelry 0
PREV_NAME_SELLER_INDUSTRY_MLM partners 0
PREV_NAME_SELLER_INDUSTRY_Tourism 0
PREV_NAME_SELLER_INDUSTRY_XNA 0
PREV_NAME_YIELD_GROUP_XNA 0
PREV_NAME_YIELD_GROUP_high 0
PREV_NAME_YIELD_GROUP_low_action 0
PREV_NAME_YIELD_GROUP_low_normal 0
PREV_NAME_YIELD_GROUP_middle 0
PREV_PRODUCT_COMBINATION_Card Street 0
PREV_PRODUCT_COMBINATION_Card X-Sell 0
PREV_PRODUCT_COMBINATION_Cash 0
PREV_PRODUCT_COMBINATION_Cash Street: high 0
PREV_PRODUCT_COMBINATION_Cash Street: low 0
PREV_PRODUCT_COMBINATION_Cash Street: middle 0
PREV_PRODUCT_COMBINATION_Cash X-Sell: high 0
PREV_PRODUCT_COMBINATION_Cash X-Sell: low 0
PREV_PRODUCT_COMBINATION_Cash X-Sell: middle 0
PREV_PRODUCT_COMBINATION_POS household with interest 0
PREV_PRODUCT_COMBINATION_POS household without interest 0
PREV_PRODUCT_COMBINATION_POS industry with interest 0
PREV_PRODUCT_COMBINATION_POS industry without interest 0
PREV_PRODUCT_COMBINATION_POS mobile with interest 0
PREV_PRODUCT_COMBINATION_POS mobile without interest 0
PREV_PRODUCT_COMBINATION_POS other with interest 0
PREV_PRODUCT_COMBINATION_POS others without interest 0
POS_MONTHS_BALANCE 0
POS_CNT_INSTALMENT 0
POS_CNT_INSTALMENT_FUTURE 0
POS_SK_DPD 0
POS_SK_DPD_DEF 0
POS_NAME_CONTRACT_STATUS_Active 0
POS_NAME_CONTRACT_STATUS_Amortized debt 0
POS_NAME_CONTRACT_STATUS_Approved 0
POS_NAME_CONTRACT_STATUS_Canceled 0
POS_NAME_CONTRACT_STATUS_Completed 0
POS_NAME_CONTRACT_STATUS_Demand 0
POS_NAME_CONTRACT_STATUS_Returned to the store 0
POS_NAME_CONTRACT_STATUS_Signed 0
POS_NAME_CONTRACT_STATUS_XNA 0
INSTA_NUM_INSTALMENT_VERSION 0
INSTA_NUM_INSTALMENT_NUMBER 0
INSTA_DAYS_INSTALMENT 0
INSTA_DAYS_ENTRY_PAYMENT 0
INSTA_AMT_INSTALMENT 0
INSTA_AMT_PAYMENT 0
CREDIT_MONTHS_BALANCE 0
CREDIT_AMT_BALANCE 0
CREDIT_AMT_CREDIT_LIMIT_ACTUAL 0
CREDIT_AMT_DRAWINGS_ATM_CURRENT 0
CREDIT_AMT_DRAWINGS_CURRENT 0
CREDIT_AMT_DRAWINGS_OTHER_CURRENT 0
CREDIT_AMT_DRAWINGS_POS_CURRENT 0
CREDIT_AMT_INST_MIN_REGULARITY 0
CREDIT_AMT_PAYMENT_CURRENT 0
CREDIT_AMT_PAYMENT_TOTAL_CURRENT 0
CREDIT_AMT_RECEIVABLE_PRINCIPAL 0
CREDIT_AMT_RECIVABLE 0
CREDIT_AMT_TOTAL_RECEIVABLE 0
CREDIT_CNT_DRAWINGS_ATM_CURRENT 0
CREDIT_CNT_DRAWINGS_CURRENT 0
CREDIT_CNT_DRAWINGS_OTHER_CURRENT 0
CREDIT_CNT_DRAWINGS_POS_CURRENT 0
CREDIT_CNT_INSTALMENT_MATURE_CUM 0
CREDIT_SK_DPD 0
CREDIT_SK_DPD_DEF 0
CREDIT_NAME_CONTRACT_STATUS_Active 0
CREDIT_NAME_CONTRACT_STATUS_Approved 0
CREDIT_NAME_CONTRACT_STATUS_Completed 0
CREDIT_NAME_CONTRACT_STATUS_Demand 0
CREDIT_NAME_CONTRACT_STATUS_Refused 0
CREDIT_NAME_CONTRACT_STATUS_Sent proposal 0
CREDIT_NAME_CONTRACT_STATUS_Signed 0


app_bure_prev.dropna(subset=['AMT_ANNUITY','ANNUITY_INCOME_PERCENT','CREDIT_TERM','AMT_GOODS_PRICE','NAME_TYPE_SUITE','OBS_30_CNT_SOCIAL_CIRCLE','DEF_30_CNT_SOCIAL_CIRCLE','OBS_60_CNT_SOCIAL_CIRCLE','DEF_60_CNT_SOCIAL_CIRCLE','DAYS_LAST_PHONE_CHANGE','EXT_SOURCE_2','CNT_FAM_MEMBERS'],inplace=True)


for col in app_bure_prev.columns:
    print(col,app_bure_prev[col].isnull().sum())

SK_ID_CURR 0
TARGET 0
NAME_CONTRACT_TYPE 0
CODE_GENDER 0
FLAG_OWN_CAR 0
FLAG_OWN_REALTY 0
CNT_CHILDREN 0
AMT_INCOME_TOTAL 0
AMT_CREDIT 0
AMT_ANNUITY 0
AMT_GOODS_PRICE 0
NAME_TYPE_SUITE 0
NAME_INCOME_TYPE 0
NAME_EDUCATION_TYPE 0
NAME_FAMILY_STATUS 0
NAME_HOUSING_TYPE 0
REGION_POPULATION_RELATIVE 0
DAYS_BIRTH 0
DAYS_EMPLOYED 0
DAYS_REGISTRATION 0
DAYS_ID_PUBLISH 0
OWN_CAR_AGE 200912
FLAG_MOBIL 0
FLAG_EMP_PHONE 0
FLAG_WORK_PHONE 0
FLAG_CONT_MOBILE 0
FLAG_PHONE 0
FLAG_EMAIL 0
OCCUPATION_TYPE 95435
CNT_FAM_MEMBERS 0
REGION_RATING_CLIENT 0
REGION_RATING_CLIENT_W_CITY 0
WEEKDAY_APPR_PROCESS_START 0
HOUR_APPR_PROCESS_START 0
REG_REGION_NOT_LIVE_REGION 0
REG_REGION_NOT_WORK_REGION 0
LIVE_REGION_NOT_WORK_REGION 0
REG_CITY_NOT_LIVE_CITY 0
REG_CITY_NOT_WORK_CITY 0
LIVE_CITY_NOT_WORK_CITY 0
ORGANIZATION_TYPE 0
EXT_SOURCE_1 171652
EXT_SOURCE_2 0
EXT_SOURCE_3 60251
APARTMENTS_AVG 154677
BASEMENTAREA_AVG 178332
YEARS_BEGINEXPLUATATION_AVG 148686
YEARS_BUILD_AVG 202604
COMMONAREA_AVG 212870
ELEVATORS_AVG 162459
ENTRANCES_AVG 153468
FLOORSMAX_AVG 151677
FLOORSMIN_AVG 206726
LANDAREA_AVG 180937
LIVINGAPARTMENTS_AVG 208259
LIVINGAREA_AVG 152985
NONLIVINGAPARTMENTS_AVG 211544
NONLIVINGAREA_AVG 168187
APARTMENTS_MODE 154677
BASEMENTAREA_MODE 178332
YEARS_BEGINEXPLUATATION_MODE 148686
YEARS_BUILD_MODE 202604
COMMONAREA_MODE 212870
ELEVATORS_MODE 162459
ENTRANCES_MODE 153468
FLOORSMAX_MODE 151677
FLOORSMIN_MODE 206726
LANDAREA_MODE 180937
LIVINGAPARTMENTS_MODE 208259
LIVINGAREA_MODE 152985
NONLIVINGAPARTMENTS_MODE 211544
NONLIVINGAREA_MODE 168187
APARTMENTS_MEDI 154677
BASEMENTAREA_MEDI 178332
YEARS_BEGINEXPLUATATION_MEDI 148686
YEARS_BUILD_MEDI 202604
COMMONAREA_MEDI 212870
ELEVATORS_MEDI 162459
ENTRANCES_MEDI 153468
FLOORSMAX_MEDI 151677
FLOORSMIN_MEDI 206726
LANDAREA_MEDI 180937
LIVINGAPARTMENTS_MEDI 208259
LIVINGAREA_MEDI 152985
NONLIVINGAPARTMENTS_MEDI 211544
NONLIVINGAREA_MEDI 168187
FONDKAPREMONT_MODE 208352
HOUSETYPE_MODE 152937
TOTALAREA_MODE 147132
WALLSMATERIAL_MODE 154978
EMERGENCYSTATE_MODE 144475
OBS_30_CNT_SOCIAL_CIRCLE 0
DEF_30_CNT_SOCIAL_CIRCLE 0
OBS_60_CNT_SOCIAL_CIRCLE 0
DEF_60_CNT_SOCIAL_CIRCLE 0
DAYS_LAST_PHONE_CHANGE 0
FLAG_DOCUMENT_2 0
FLAG_DOCUMENT_3 0
FLAG_DOCUMENT_4 0
FLAG_DOCUMENT_5 0
FLAG_DOCUMENT_6 0
FLAG_DOCUMENT_7 0
FLAG_DOCUMENT_8 0
FLAG_DOCUMENT_9 0
FLAG_DOCUMENT_10 0
FLAG_DOCUMENT_11 0
FLAG_DOCUMENT_12 0
FLAG_DOCUMENT_13 0
FLAG_DOCUMENT_14 0
FLAG_DOCUMENT_15 0
FLAG_DOCUMENT_16 0
FLAG_DOCUMENT_17 0
FLAG_DOCUMENT_18 0
FLAG_DOCUMENT_19 0
FLAG_DOCUMENT_20 0
FLAG_DOCUMENT_21 0
AMT_REQ_CREDIT_BUREAU_HOUR 41108
AMT_REQ_CREDIT_BUREAU_DAY 41108
AMT_REQ_CREDIT_BUREAU_WEEK 41108
AMT_REQ_CREDIT_BUREAU_MON 41108
AMT_REQ_CREDIT_BUREAU_QRT 41108
AMT_REQ_CREDIT_BUREAU_YEAR 41108
INCOME_GT_CREDIT_FLAG 0
CREDIT_INCOME_PERCENT 0
ANNUITY_INCOME_PERCENT 0
CREDIT_TERM 0
DAYS_EMPLOYED_PERCENT 0
BUREAU_DAYS_CREDIT 0
BUREAU_CREDIT_DAY_OVERDUE 0
BUREAU_DAYS_CREDIT_ENDDATE 0
BUREAU_DAYS_ENDDATE_FACT 0
BUREAU_AMT_CREDIT_MAX_OVERDUE 0
BUREAU_CNT_CREDIT_PROLONG 0
BUREAU_AMT_CREDIT_SUM 0
BUREAU_AMT_CREDIT_SUM_DEBT 0
BUREAU_AMT_CREDIT_SUM_LIMIT 0
BUREAU_AMT_CREDIT_SUM_OVERDUE 0
BUREAU_DAYS_CREDIT_UPDATE 0
BUREAU_AMT_ANNUITY 0
BUREAU_CREDIT_ACTIVE_Active 0
BUREAU_CREDIT_ACTIVE_Bad debt 0
BUREAU_CREDIT_ACTIVE_Closed 0
BUREAU_CREDIT_ACTIVE_Sold 0
BUREAU_CREDIT_CURRENCY_currency 1 0
BUREAU_CREDIT_CURRENCY_currency 2 0
BUREAU_CREDIT_CURRENCY_currency 3 0
BUREAU_CREDIT_CURRENCY_currency 4 0
BUREAU_CREDIT_TYPE_Another type of loan 0
BUREAU_CREDIT_TYPE_Car loan 0
BUREAU_CREDIT_TYPE_Cash loan (non-earmarked) 0
BUREAU_CREDIT_TYPE_Consumer credit 0
BUREAU_CREDIT_TYPE_Credit card 0
BUREAU_CREDIT_TYPE_Interbank credit 0
BUREAU_CREDIT_TYPE_Loan for business development 0
BUREAU_CREDIT_TYPE_Loan for purchase of shares (margin lending) 0
BUREAU_CREDIT_TYPE_Loan for the purchase of equipment 0
BUREAU_CREDIT_TYPE_Loan for working capital replenishment 0
BUREAU_CREDIT_TYPE_Microloan 0
BUREAU_CREDIT_TYPE_Mobile operator loan 0
BUREAU_CREDIT_TYPE_Mortgage 0
BUREAU_CREDIT_TYPE_Real estate loan 0
BUREAU_CREDIT_TYPE_Unknown type of loan 0
PREV_APP_COUNT 0
PREV_AMT_ANNUITY 0
PREV_AMT_APPLICATION 0
PREV_AMT_CREDIT 0
PREV_AMT_DOWN_PAYMENT 0
PREV_AMT_GOODS_PRICE 0
PREV_HOUR_APPR_PROCESS_START 0
PREV_NFLAG_LAST_APPL_IN_DAY 0
PREV_RATE_DOWN_PAYMENT 0
PREV_RATE_INTEREST_PRIMARY 0
PREV_RATE_INTEREST_PRIVILEGED 0
PREV_DAYS_DECISION 0
PREV_SELLERPLACE_AREA 0
PREV_CNT_PAYMENT 0
PREV_DAYS_FIRST_DRAWING 0
PREV_DAYS_FIRST_DUE 0
PREV_DAYS_LAST_DUE_1ST_VERSION 0
PREV_DAYS_LAST_DUE 0
PREV_DAYS_TERMINATION 0
PREV_NFLAG_INSURED_ON_APPROVAL 0
PREV_NAME_CONTRACT_TYPE_Cash loans 0
PREV_NAME_CONTRACT_TYPE_Consumer loans 0
PREV_NAME_CONTRACT_TYPE_Revolving loans 0
PREV_NAME_CONTRACT_TYPE_XNA 0
PREV_WEEKDAY_APPR_PROCESS_START_FRIDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_MONDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_SATURDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_SUNDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_THURSDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_TUESDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_WEDNESDAY 0
PREV_FLAG_LAST_APPL_PER_CONTRACT_N 0
PREV_FLAG_LAST_APPL_PER_CONTRACT_Y 0
PREV_NAME_CASH_LOAN_PURPOSE_Building a house or an annex 0
PREV_NAME_CASH_LOAN_PURPOSE_Business development 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a garage 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a holiday home / land 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a home 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a new car 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a used car 0
PREV_NAME_CASH_LOAN_PURPOSE_Car repairs 0
PREV_NAME_CASH_LOAN_PURPOSE_Education 0
PREV_NAME_CASH_LOAN_PURPOSE_Everyday expenses 0
PREV_NAME_CASH_LOAN_PURPOSE_Furniture 0
PREV_NAME_CASH_LOAN_PURPOSE_Gasification / water supply 0
PREV_NAME_CASH_LOAN_PURPOSE_Hobby 0
PREV_NAME_CASH_LOAN_PURPOSE_Journey 0
PREV_NAME_CASH_LOAN_PURPOSE_Medicine 0
PREV_NAME_CASH_LOAN_PURPOSE_Money for a third person 0
PREV_NAME_CASH_LOAN_PURPOSE_Other 0
PREV_NAME_CASH_LOAN_PURPOSE_Payments on other loans 0
PREV_NAME_CASH_LOAN_PURPOSE_Purchase of electronic equipment 0
PREV_NAME_CASH_LOAN_PURPOSE_Refusal to name the goal 0
PREV_NAME_CASH_LOAN_PURPOSE_Repairs 0
PREV_NAME_CASH_LOAN_PURPOSE_Urgent needs 0
PREV_NAME_CASH_LOAN_PURPOSE_Wedding / gift / holiday 0
PREV_NAME_CASH_LOAN_PURPOSE_XAP 0
PREV_NAME_CASH_LOAN_PURPOSE_XNA 0
PREV_NAME_CONTRACT_STATUS_Approved 0
PREV_NAME_CONTRACT_STATUS_Canceled 0
PREV_NAME_CONTRACT_STATUS_Refused 0
PREV_NAME_CONTRACT_STATUS_Unused offer 0
PREV_NAME_PAYMENT_TYPE_Cash through the bank 0
PREV_NAME_PAYMENT_TYPE_Cashless from the account of the employer 0
PREV_NAME_PAYMENT_TYPE_Non-cash from your account 0
PREV_NAME_PAYMENT_TYPE_XNA 0
PREV_CODE_REJECT_REASON_CLIENT 0
PREV_CODE_REJECT_REASON_HC 0
PREV_CODE_REJECT_REASON_LIMIT 0
PREV_CODE_REJECT_REASON_SCO 0
PREV_CODE_REJECT_REASON_SCOFR 0
PREV_CODE_REJECT_REASON_SYSTEM 0
PREV_CODE_REJECT_REASON_VERIF 0
PREV_CODE_REJECT_REASON_XAP 0
PREV_CODE_REJECT_REASON_XNA 0
PREV_NAME_TYPE_SUITE_Children 0
PREV_NAME_TYPE_SUITE_Family 0
PREV_NAME_TYPE_SUITE_Group of people 0
PREV_NAME_TYPE_SUITE_Other_A 0
PREV_NAME_TYPE_SUITE_Other_B 0
PREV_NAME_TYPE_SUITE_Spouse, partner 0
PREV_NAME_TYPE_SUITE_Unaccompanied 0
PREV_NAME_CLIENT_TYPE_New 0
PREV_NAME_CLIENT_TYPE_Refreshed 0
PREV_NAME_CLIENT_TYPE_Repeater 0
PREV_NAME_CLIENT_TYPE_XNA 0
PREV_NAME_GOODS_CATEGORY_Additional Service 0
PREV_NAME_GOODS_CATEGORY_Animals 0
PREV_NAME_GOODS_CATEGORY_Audio/Video 0
PREV_NAME_GOODS_CATEGORY_Auto Accessories 0
PREV_NAME_GOODS_CATEGORY_Clothing and Accessories 0
PREV_NAME_GOODS_CATEGORY_Computers 0
PREV_NAME_GOODS_CATEGORY_Construction Materials 0
PREV_NAME_GOODS_CATEGORY_Consumer Electronics 0
PREV_NAME_GOODS_CATEGORY_Direct Sales 0
PREV_NAME_GOODS_CATEGORY_Education 0
PREV_NAME_GOODS_CATEGORY_Fitness 0
PREV_NAME_GOODS_CATEGORY_Furniture 0
PREV_NAME_GOODS_CATEGORY_Gardening 0
PREV_NAME_GOODS_CATEGORY_Homewares 0
PREV_NAME_GOODS_CATEGORY_House Construction 0
PREV_NAME_GOODS_CATEGORY_Insurance 0
PREV_NAME_GOODS_CATEGORY_Jewelry 0
PREV_NAME_GOODS_CATEGORY_Medical Supplies 0
PREV_NAME_GOODS_CATEGORY_Medicine 0
PREV_NAME_GOODS_CATEGORY_Mobile 0
PREV_NAME_GOODS_CATEGORY_Office Appliances 0
PREV_NAME_GOODS_CATEGORY_Other 0
PREV_NAME_GOODS_CATEGORY_Photo / Cinema Equipment 0
PREV_NAME_GOODS_CATEGORY_Sport and Leisure 0
PREV_NAME_GOODS_CATEGORY_Tourism 0
PREV_NAME_GOODS_CATEGORY_Vehicles 0
PREV_NAME_GOODS_CATEGORY_Weapon 0
PREV_NAME_GOODS_CATEGORY_XNA 0
PREV_NAME_PORTFOLIO_Cards 0
PREV_NAME_PORTFOLIO_Cars 0
PREV_NAME_PORTFOLIO_Cash 0
PREV_NAME_PORTFOLIO_POS 0
PREV_NAME_PORTFOLIO_XNA 0
PREV_NAME_PRODUCT_TYPE_XNA 0
PREV_NAME_PRODUCT_TYPE_walk-in 0
PREV_NAME_PRODUCT_TYPE_x-sell 0
PREV_CHANNEL_TYPE_AP+ (Cash loan) 0
PREV_CHANNEL_TYPE_Car dealer 0
PREV_CHANNEL_TYPE_Channel of corporate sales 0
PREV_CHANNEL_TYPE_Contact center 0
PREV_CHANNEL_TYPE_Country-wide 0
PREV_CHANNEL_TYPE_Credit and cash offices 0
PREV_CHANNEL_TYPE_Regional / Local 0
PREV_CHANNEL_TYPE_Stone 0
PREV_NAME_SELLER_INDUSTRY_Auto technology 0
PREV_NAME_SELLER_INDUSTRY_Clothing 0
PREV_NAME_SELLER_INDUSTRY_Connectivity 0
PREV_NAME_SELLER_INDUSTRY_Construction 0
PREV_NAME_SELLER_INDUSTRY_Consumer electronics 0
PREV_NAME_SELLER_INDUSTRY_Furniture 0
PREV_NAME_SELLER_INDUSTRY_Industry 0
PREV_NAME_SELLER_INDUSTRY_Jewelry 0
PREV_NAME_SELLER_INDUSTRY_MLM partners 0
PREV_NAME_SELLER_INDUSTRY_Tourism 0
PREV_NAME_SELLER_INDUSTRY_XNA 0
PREV_NAME_YIELD_GROUP_XNA 0
PREV_NAME_YIELD_GROUP_high 0
PREV_NAME_YIELD_GROUP_low_action 0
PREV_NAME_YIELD_GROUP_low_normal 0
PREV_NAME_YIELD_GROUP_middle 0
PREV_PRODUCT_COMBINATION_Card Street 0
PREV_PRODUCT_COMBINATION_Card X-Sell 0
PREV_PRODUCT_COMBINATION_Cash 0
PREV_PRODUCT_COMBINATION_Cash Street: high 0
PREV_PRODUCT_COMBINATION_Cash Street: low 0
PREV_PRODUCT_COMBINATION_Cash Street: middle 0
PREV_PRODUCT_COMBINATION_Cash X-Sell: high 0
PREV_PRODUCT_COMBINATION_Cash X-Sell: low 0
PREV_PRODUCT_COMBINATION_Cash X-Sell: middle 0
PREV_PRODUCT_COMBINATION_POS household with interest 0
PREV_PRODUCT_COMBINATION_POS household without interest 0
PREV_PRODUCT_COMBINATION_POS industry with interest 0
PREV_PRODUCT_COMBINATION_POS industry without interest 0
PREV_PRODUCT_COMBINATION_POS mobile with interest 0
PREV_PRODUCT_COMBINATION_POS mobile without interest 0
PREV_PRODUCT_COMBINATION_POS other with interest 0
PREV_PRODUCT_COMBINATION_POS others without interest 0
POS_MONTHS_BALANCE 0
POS_CNT_INSTALMENT 0
POS_CNT_INSTALMENT_FUTURE 0
POS_SK_DPD 0
POS_SK_DPD_DEF 0
POS_NAME_CONTRACT_STATUS_Active 0
POS_NAME_CONTRACT_STATUS_Amortized debt 0
POS_NAME_CONTRACT_STATUS_Approved 0
POS_NAME_CONTRACT_STATUS_Canceled 0
POS_NAME_CONTRACT_STATUS_Completed 0
POS_NAME_CONTRACT_STATUS_Demand 0
POS_NAME_CONTRACT_STATUS_Returned to the store 0
POS_NAME_CONTRACT_STATUS_Signed 0
POS_NAME_CONTRACT_STATUS_XNA 0
INSTA_NUM_INSTALMENT_VERSION 0
INSTA_NUM_INSTALMENT_NUMBER 0
INSTA_DAYS_INSTALMENT 0
INSTA_DAYS_ENTRY_PAYMENT 0
INSTA_AMT_INSTALMENT 0
INSTA_AMT_PAYMENT 0
CREDIT_MONTHS_BALANCE 0
CREDIT_AMT_BALANCE 0
CREDIT_AMT_CREDIT_LIMIT_ACTUAL 0
CREDIT_AMT_DRAWINGS_ATM_CURRENT 0
CREDIT_AMT_DRAWINGS_CURRENT 0
CREDIT_AMT_DRAWINGS_OTHER_CURRENT 0
CREDIT_AMT_DRAWINGS_POS_CURRENT 0
CREDIT_AMT_INST_MIN_REGULARITY 0
CREDIT_AMT_PAYMENT_CURRENT 0
CREDIT_AMT_PAYMENT_TOTAL_CURRENT 0
CREDIT_AMT_RECEIVABLE_PRINCIPAL 0
CREDIT_AMT_RECIVABLE 0
CREDIT_AMT_TOTAL_RECEIVABLE 0
CREDIT_CNT_DRAWINGS_ATM_CURRENT 0
CREDIT_CNT_DRAWINGS_CURRENT 0
CREDIT_CNT_DRAWINGS_OTHER_CURRENT 0
CREDIT_CNT_DRAWINGS_POS_CURRENT 0
CREDIT_CNT_INSTALMENT_MATURE_CUM 0
CREDIT_SK_DPD 0
CREDIT_SK_DPD_DEF 0
CREDIT_NAME_CONTRACT_STATUS_Active 0
CREDIT_NAME_CONTRACT_STATUS_Approved 0
CREDIT_NAME_CONTRACT_STATUS_Completed 0
CREDIT_NAME_CONTRACT_STATUS_Demand 0
CREDIT_NAME_CONTRACT_STATUS_Refused 0
CREDIT_NAME_CONTRACT_STATUS_Sent proposal 0
CREDIT_NAME_CONTRACT_STATUS_Signed 0


start_h=app_train.columns.get_loc("OWN_CAR_AGE")
end_h=app_bure_prev.columns.get_loc("WALLSMATERIAL_MODE")

df_house=app_bure_prev.iloc[:,start_h:end_h+1]
df_house["TARGET"]=app_bure_prev["TARGET"]
df_house["NAME_HOUSING_TYPE"]=app_bure_prev["NAME_HOUSING_TYPE"]


start_hou=df_house.columns.get_loc("OWN_CAR_AGE")
end_hou=df_house.columns.get_loc("WALLSMATERIAL_MODE")

house_df=df_house.iloc[:,start_hou:end_hou+1]


# plt.figure(figsize=(25,20))
# sns.heatmap(house_df.corr(),annot=True)


app_bure_prev.drop(['EXT_SOURCE_1',
'APARTMENTS_AVG',
'BASEMENTAREA_AVG',
'YEARS_BUILD_AVG',
'COMMONAREA_AVG',
'ELEVATORS_AVG',
'ENTRANCES_AVG',
'FLOORSMAX_AVG',
'FLOORSMIN_AVG',
'LANDAREA_AVG',
'LIVINGAPARTMENTS_AVG',
'LIVINGAREA_AVG',
'NONLIVINGAPARTMENTS_AVG',
'NONLIVINGAREA_AVG',
'APARTMENTS_MODE',
'BASEMENTAREA_MODE',
'YEARS_BUILD_MODE',
'COMMONAREA_MODE',
'ELEVATORS_MODE',
'ENTRANCES_MODE',
'FLOORSMAX_MODE',
'FLOORSMIN_MODE',
'LANDAREA_MODE',
'LIVINGAPARTMENTS_MODE',
'LIVINGAREA_MODE',
'NONLIVINGAPARTMENTS_MODE',
'NONLIVINGAREA_MODE',
'APARTMENTS_MEDI',
'BASEMENTAREA_MEDI',
'YEARS_BUILD_MEDI',
'COMMONAREA_MEDI',
'ELEVATORS_MEDI',
'ENTRANCES_MEDI',
'FLOORSMAX_MEDI',
'FLOORSMIN_MEDI',
'LANDAREA_MEDI',
'LIVINGAPARTMENTS_MEDI',
'LIVINGAREA_MEDI',
'NONLIVINGAPARTMENTS_MEDI',
'NONLIVINGAREA_MEDI',
'FONDKAPREMONT_MODE',
'HOUSETYPE_MODE',
'WALLSMATERIAL_MODE'],axis=1,inplace=True)


for col in app_bure_prev.columns:
    print(col,app_bure_prev[col].isnull().sum())

SK_ID_CURR 0
TARGET 0
NAME_CONTRACT_TYPE 0
CODE_GENDER 0
FLAG_OWN_CAR 0
FLAG_OWN_REALTY 0
CNT_CHILDREN 0
AMT_INCOME_TOTAL 0
AMT_CREDIT 0
AMT_ANNUITY 0
AMT_GOODS_PRICE 0
NAME_TYPE_SUITE 0
NAME_INCOME_TYPE 0
NAME_EDUCATION_TYPE 0
NAME_FAMILY_STATUS 0
NAME_HOUSING_TYPE 0
REGION_POPULATION_RELATIVE 0
DAYS_BIRTH 0
DAYS_EMPLOYED 0
DAYS_REGISTRATION 0
DAYS_ID_PUBLISH 0
OWN_CAR_AGE 200912
FLAG_MOBIL 0
FLAG_EMP_PHONE 0
FLAG_WORK_PHONE 0
FLAG_CONT_MOBILE 0
FLAG_PHONE 0
FLAG_EMAIL 0
OCCUPATION_TYPE 95435
CNT_FAM_MEMBERS 0
REGION_RATING_CLIENT 0
REGION_RATING_CLIENT_W_CITY 0
WEEKDAY_APPR_PROCESS_START 0
HOUR_APPR_PROCESS_START 0
REG_REGION_NOT_LIVE_REGION 0
REG_REGION_NOT_WORK_REGION 0
LIVE_REGION_NOT_WORK_REGION 0
REG_CITY_NOT_LIVE_CITY 0
REG_CITY_NOT_WORK_CITY 0
LIVE_CITY_NOT_WORK_CITY 0
ORGANIZATION_TYPE 0
EXT_SOURCE_2 0
EXT_SOURCE_3 60251
YEARS_BEGINEXPLUATATION_AVG 148686
YEARS_BEGINEXPLUATATION_MODE 148686
YEARS_BEGINEXPLUATATION_MEDI 148686
TOTALAREA_MODE 147132
EMERGENCYSTATE_MODE 144475
OBS_30_CNT_SOCIAL_CIRCLE 0
DEF_30_CNT_SOCIAL_CIRCLE 0
OBS_60_CNT_SOCIAL_CIRCLE 0
DEF_60_CNT_SOCIAL_CIRCLE 0
DAYS_LAST_PHONE_CHANGE 0
FLAG_DOCUMENT_2 0
FLAG_DOCUMENT_3 0
FLAG_DOCUMENT_4 0
FLAG_DOCUMENT_5 0
FLAG_DOCUMENT_6 0
FLAG_DOCUMENT_7 0
FLAG_DOCUMENT_8 0
FLAG_DOCUMENT_9 0
FLAG_DOCUMENT_10 0
FLAG_DOCUMENT_11 0
FLAG_DOCUMENT_12 0
FLAG_DOCUMENT_13 0
FLAG_DOCUMENT_14 0
FLAG_DOCUMENT_15 0
FLAG_DOCUMENT_16 0
FLAG_DOCUMENT_17 0
FLAG_DOCUMENT_18 0
FLAG_DOCUMENT_19 0
FLAG_DOCUMENT_20 0
FLAG_DOCUMENT_21 0
AMT_REQ_CREDIT_BUREAU_HOUR 41108
AMT_REQ_CREDIT_BUREAU_DAY 41108
AMT_REQ_CREDIT_BUREAU_WEEK 41108
AMT_REQ_CREDIT_BUREAU_MON 41108
AMT_REQ_CREDIT_BUREAU_QRT 41108
AMT_REQ_CREDIT_BUREAU_YEAR 41108
INCOME_GT_CREDIT_FLAG 0
CREDIT_INCOME_PERCENT 0
ANNUITY_INCOME_PERCENT 0
CREDIT_TERM 0
DAYS_EMPLOYED_PERCENT 0
BUREAU_DAYS_CREDIT 0
BUREAU_CREDIT_DAY_OVERDUE 0
BUREAU_DAYS_CREDIT_ENDDATE 0
BUREAU_DAYS_ENDDATE_FACT 0
BUREAU_AMT_CREDIT_MAX_OVERDUE 0
BUREAU_CNT_CREDIT_PROLONG 0
BUREAU_AMT_CREDIT_SUM 0
BUREAU_AMT_CREDIT_SUM_DEBT 0
BUREAU_AMT_CREDIT_SUM_LIMIT 0
BUREAU_AMT_CREDIT_SUM_OVERDUE 0
BUREAU_DAYS_CREDIT_UPDATE 0
BUREAU_AMT_ANNUITY 0
BUREAU_CREDIT_ACTIVE_Active 0
BUREAU_CREDIT_ACTIVE_Bad debt 0
BUREAU_CREDIT_ACTIVE_Closed 0
BUREAU_CREDIT_ACTIVE_Sold 0
BUREAU_CREDIT_CURRENCY_currency 1 0
BUREAU_CREDIT_CURRENCY_currency 2 0
BUREAU_CREDIT_CURRENCY_currency 3 0
BUREAU_CREDIT_CURRENCY_currency 4 0
BUREAU_CREDIT_TYPE_Another type of loan 0
BUREAU_CREDIT_TYPE_Car loan 0
BUREAU_CREDIT_TYPE_Cash loan (non-earmarked) 0
BUREAU_CREDIT_TYPE_Consumer credit 0
BUREAU_CREDIT_TYPE_Credit card 0
BUREAU_CREDIT_TYPE_Interbank credit 0
BUREAU_CREDIT_TYPE_Loan for business development 0
BUREAU_CREDIT_TYPE_Loan for purchase of shares (margin lending) 0
BUREAU_CREDIT_TYPE_Loan for the purchase of equipment 0
BUREAU_CREDIT_TYPE_Loan for working capital replenishment 0
BUREAU_CREDIT_TYPE_Microloan 0
BUREAU_CREDIT_TYPE_Mobile operator loan 0
BUREAU_CREDIT_TYPE_Mortgage 0
BUREAU_CREDIT_TYPE_Real estate loan 0
BUREAU_CREDIT_TYPE_Unknown type of loan 0
PREV_APP_COUNT 0
PREV_AMT_ANNUITY 0
PREV_AMT_APPLICATION 0
PREV_AMT_CREDIT 0
PREV_AMT_DOWN_PAYMENT 0
PREV_AMT_GOODS_PRICE 0
PREV_HOUR_APPR_PROCESS_START 0
PREV_NFLAG_LAST_APPL_IN_DAY 0
PREV_RATE_DOWN_PAYMENT 0
PREV_RATE_INTEREST_PRIMARY 0
PREV_RATE_INTEREST_PRIVILEGED 0
PREV_DAYS_DECISION 0
PREV_SELLERPLACE_AREA 0
PREV_CNT_PAYMENT 0
PREV_DAYS_FIRST_DRAWING 0
PREV_DAYS_FIRST_DUE 0
PREV_DAYS_LAST_DUE_1ST_VERSION 0
PREV_DAYS_LAST_DUE 0
PREV_DAYS_TERMINATION 0
PREV_NFLAG_INSURED_ON_APPROVAL 0
PREV_NAME_CONTRACT_TYPE_Cash loans 0
PREV_NAME_CONTRACT_TYPE_Consumer loans 0
PREV_NAME_CONTRACT_TYPE_Revolving loans 0
PREV_NAME_CONTRACT_TYPE_XNA 0
PREV_WEEKDAY_APPR_PROCESS_START_FRIDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_MONDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_SATURDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_SUNDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_THURSDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_TUESDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_WEDNESDAY 0
PREV_FLAG_LAST_APPL_PER_CONTRACT_N 0
PREV_FLAG_LAST_APPL_PER_CONTRACT_Y 0
PREV_NAME_CASH_LOAN_PURPOSE_Building a house or an annex 0
PREV_NAME_CASH_LOAN_PURPOSE_Business development 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a garage 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a holiday home / land 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a home 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a new car 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a used car 0
PREV_NAME_CASH_LOAN_PURPOSE_Car repairs 0
PREV_NAME_CASH_LOAN_PURPOSE_Education 0
PREV_NAME_CASH_LOAN_PURPOSE_Everyday expenses 0
PREV_NAME_CASH_LOAN_PURPOSE_Furniture 0
PREV_NAME_CASH_LOAN_PURPOSE_Gasification / water supply 0
PREV_NAME_CASH_LOAN_PURPOSE_Hobby 0
PREV_NAME_CASH_LOAN_PURPOSE_Journey 0
PREV_NAME_CASH_LOAN_PURPOSE_Medicine 0
PREV_NAME_CASH_LOAN_PURPOSE_Money for a third person 0
PREV_NAME_CASH_LOAN_PURPOSE_Other 0
PREV_NAME_CASH_LOAN_PURPOSE_Payments on other loans 0
PREV_NAME_CASH_LOAN_PURPOSE_Purchase of electronic equipment 0
PREV_NAME_CASH_LOAN_PURPOSE_Refusal to name the goal 0
PREV_NAME_CASH_LOAN_PURPOSE_Repairs 0
PREV_NAME_CASH_LOAN_PURPOSE_Urgent needs 0
PREV_NAME_CASH_LOAN_PURPOSE_Wedding / gift / holiday 0
PREV_NAME_CASH_LOAN_PURPOSE_XAP 0
PREV_NAME_CASH_LOAN_PURPOSE_XNA 0
PREV_NAME_CONTRACT_STATUS_Approved 0
PREV_NAME_CONTRACT_STATUS_Canceled 0
PREV_NAME_CONTRACT_STATUS_Refused 0
PREV_NAME_CONTRACT_STATUS_Unused offer 0
PREV_NAME_PAYMENT_TYPE_Cash through the bank 0
PREV_NAME_PAYMENT_TYPE_Cashless from the account of the employer 0
PREV_NAME_PAYMENT_TYPE_Non-cash from your account 0
PREV_NAME_PAYMENT_TYPE_XNA 0
PREV_CODE_REJECT_REASON_CLIENT 0
PREV_CODE_REJECT_REASON_HC 0
PREV_CODE_REJECT_REASON_LIMIT 0
PREV_CODE_REJECT_REASON_SCO 0
PREV_CODE_REJECT_REASON_SCOFR 0
PREV_CODE_REJECT_REASON_SYSTEM 0
PREV_CODE_REJECT_REASON_VERIF 0
PREV_CODE_REJECT_REASON_XAP 0
PREV_CODE_REJECT_REASON_XNA 0
PREV_NAME_TYPE_SUITE_Children 0
PREV_NAME_TYPE_SUITE_Family 0
PREV_NAME_TYPE_SUITE_Group of people 0
PREV_NAME_TYPE_SUITE_Other_A 0
PREV_NAME_TYPE_SUITE_Other_B 0
PREV_NAME_TYPE_SUITE_Spouse, partner 0
PREV_NAME_TYPE_SUITE_Unaccompanied 0
PREV_NAME_CLIENT_TYPE_New 0
PREV_NAME_CLIENT_TYPE_Refreshed 0
PREV_NAME_CLIENT_TYPE_Repeater 0
PREV_NAME_CLIENT_TYPE_XNA 0
PREV_NAME_GOODS_CATEGORY_Additional Service 0
PREV_NAME_GOODS_CATEGORY_Animals 0
PREV_NAME_GOODS_CATEGORY_Audio/Video 0
PREV_NAME_GOODS_CATEGORY_Auto Accessories 0
PREV_NAME_GOODS_CATEGORY_Clothing and Accessories 0
PREV_NAME_GOODS_CATEGORY_Computers 0
PREV_NAME_GOODS_CATEGORY_Construction Materials 0
PREV_NAME_GOODS_CATEGORY_Consumer Electronics 0
PREV_NAME_GOODS_CATEGORY_Direct Sales 0
PREV_NAME_GOODS_CATEGORY_Education 0
PREV_NAME_GOODS_CATEGORY_Fitness 0
PREV_NAME_GOODS_CATEGORY_Furniture 0
PREV_NAME_GOODS_CATEGORY_Gardening 0
PREV_NAME_GOODS_CATEGORY_Homewares 0
PREV_NAME_GOODS_CATEGORY_House Construction 0
PREV_NAME_GOODS_CATEGORY_Insurance 0
PREV_NAME_GOODS_CATEGORY_Jewelry 0
PREV_NAME_GOODS_CATEGORY_Medical Supplies 0
PREV_NAME_GOODS_CATEGORY_Medicine 0
PREV_NAME_GOODS_CATEGORY_Mobile 0
PREV_NAME_GOODS_CATEGORY_Office Appliances 0
PREV_NAME_GOODS_CATEGORY_Other 0
PREV_NAME_GOODS_CATEGORY_Photo / Cinema Equipment 0
PREV_NAME_GOODS_CATEGORY_Sport and Leisure 0
PREV_NAME_GOODS_CATEGORY_Tourism 0
PREV_NAME_GOODS_CATEGORY_Vehicles 0
PREV_NAME_GOODS_CATEGORY_Weapon 0
PREV_NAME_GOODS_CATEGORY_XNA 0
PREV_NAME_PORTFOLIO_Cards 0
PREV_NAME_PORTFOLIO_Cars 0
PREV_NAME_PORTFOLIO_Cash 0
PREV_NAME_PORTFOLIO_POS 0
PREV_NAME_PORTFOLIO_XNA 0
PREV_NAME_PRODUCT_TYPE_XNA 0
PREV_NAME_PRODUCT_TYPE_walk-in 0
PREV_NAME_PRODUCT_TYPE_x-sell 0
PREV_CHANNEL_TYPE_AP+ (Cash loan) 0
PREV_CHANNEL_TYPE_Car dealer 0
PREV_CHANNEL_TYPE_Channel of corporate sales 0
PREV_CHANNEL_TYPE_Contact center 0
PREV_CHANNEL_TYPE_Country-wide 0
PREV_CHANNEL_TYPE_Credit and cash offices 0
PREV_CHANNEL_TYPE_Regional / Local 0
PREV_CHANNEL_TYPE_Stone 0
PREV_NAME_SELLER_INDUSTRY_Auto technology 0
PREV_NAME_SELLER_INDUSTRY_Clothing 0
PREV_NAME_SELLER_INDUSTRY_Connectivity 0
PREV_NAME_SELLER_INDUSTRY_Construction 0
PREV_NAME_SELLER_INDUSTRY_Consumer electronics 0
PREV_NAME_SELLER_INDUSTRY_Furniture 0
PREV_NAME_SELLER_INDUSTRY_Industry 0
PREV_NAME_SELLER_INDUSTRY_Jewelry 0
PREV_NAME_SELLER_INDUSTRY_MLM partners 0
PREV_NAME_SELLER_INDUSTRY_Tourism 0
PREV_NAME_SELLER_INDUSTRY_XNA 0
PREV_NAME_YIELD_GROUP_XNA 0
PREV_NAME_YIELD_GROUP_high 0
PREV_NAME_YIELD_GROUP_low_action 0
PREV_NAME_YIELD_GROUP_low_normal 0
PREV_NAME_YIELD_GROUP_middle 0
PREV_PRODUCT_COMBINATION_Card Street 0
PREV_PRODUCT_COMBINATION_Card X-Sell 0
PREV_PRODUCT_COMBINATION_Cash 0
PREV_PRODUCT_COMBINATION_Cash Street: high 0
PREV_PRODUCT_COMBINATION_Cash Street: low 0
PREV_PRODUCT_COMBINATION_Cash Street: middle 0
PREV_PRODUCT_COMBINATION_Cash X-Sell: high 0
PREV_PRODUCT_COMBINATION_Cash X-Sell: low 0
PREV_PRODUCT_COMBINATION_Cash X-Sell: middle 0
PREV_PRODUCT_COMBINATION_POS household with interest 0
PREV_PRODUCT_COMBINATION_POS household without interest 0
PREV_PRODUCT_COMBINATION_POS industry with interest 0
PREV_PRODUCT_COMBINATION_POS industry without interest 0
PREV_PRODUCT_COMBINATION_POS mobile with interest 0
PREV_PRODUCT_COMBINATION_POS mobile without interest 0
PREV_PRODUCT_COMBINATION_POS other with interest 0
PREV_PRODUCT_COMBINATION_POS others without interest 0
POS_MONTHS_BALANCE 0
POS_CNT_INSTALMENT 0
POS_CNT_INSTALMENT_FUTURE 0
POS_SK_DPD 0
POS_SK_DPD_DEF 0
POS_NAME_CONTRACT_STATUS_Active 0
POS_NAME_CONTRACT_STATUS_Amortized debt 0
POS_NAME_CONTRACT_STATUS_Approved 0
POS_NAME_CONTRACT_STATUS_Canceled 0
POS_NAME_CONTRACT_STATUS_Completed 0
POS_NAME_CONTRACT_STATUS_Demand 0
POS_NAME_CONTRACT_STATUS_Returned to the store 0
POS_NAME_CONTRACT_STATUS_Signed 0
POS_NAME_CONTRACT_STATUS_XNA 0
INSTA_NUM_INSTALMENT_VERSION 0
INSTA_NUM_INSTALMENT_NUMBER 0
INSTA_DAYS_INSTALMENT 0
INSTA_DAYS_ENTRY_PAYMENT 0
INSTA_AMT_INSTALMENT 0
INSTA_AMT_PAYMENT 0
CREDIT_MONTHS_BALANCE 0
CREDIT_AMT_BALANCE 0
CREDIT_AMT_CREDIT_LIMIT_ACTUAL 0
CREDIT_AMT_DRAWINGS_ATM_CURRENT 0
CREDIT_AMT_DRAWINGS_CURRENT 0
CREDIT_AMT_DRAWINGS_OTHER_CURRENT 0
CREDIT_AMT_DRAWINGS_POS_CURRENT 0
CREDIT_AMT_INST_MIN_REGULARITY 0
CREDIT_AMT_PAYMENT_CURRENT 0
CREDIT_AMT_PAYMENT_TOTAL_CURRENT 0
CREDIT_AMT_RECEIVABLE_PRINCIPAL 0
CREDIT_AMT_RECIVABLE 0
CREDIT_AMT_TOTAL_RECEIVABLE 0
CREDIT_CNT_DRAWINGS_ATM_CURRENT 0
CREDIT_CNT_DRAWINGS_CURRENT 0
CREDIT_CNT_DRAWINGS_OTHER_CURRENT 0
CREDIT_CNT_DRAWINGS_POS_CURRENT 0
CREDIT_CNT_INSTALMENT_MATURE_CUM 0
CREDIT_SK_DPD 0
CREDIT_SK_DPD_DEF 0
CREDIT_NAME_CONTRACT_STATUS_Active 0
CREDIT_NAME_CONTRACT_STATUS_Approved 0
CREDIT_NAME_CONTRACT_STATUS_Completed 0
CREDIT_NAME_CONTRACT_STATUS_Demand 0
CREDIT_NAME_CONTRACT_STATUS_Refused 0
CREDIT_NAME_CONTRACT_STATUS_Sent proposal 0
CREDIT_NAME_CONTRACT_STATUS_Signed 0


app_bure_prev["AMT_REQ_CREDIT_BUREAU_HOUR"].fillna(app_train["AMT_REQ_CREDIT_BUREAU_HOUR"].median(),inplace=True)
app_bure_prev["AMT_REQ_CREDIT_BUREAU_DAY"].fillna(app_train["AMT_REQ_CREDIT_BUREAU_DAY"].median(),inplace=True)
app_bure_prev["AMT_REQ_CREDIT_BUREAU_WEEK"].fillna(app_train["AMT_REQ_CREDIT_BUREAU_WEEK"].median(),inplace=True)
app_bure_prev["AMT_REQ_CREDIT_BUREAU_MON"].fillna(app_train["AMT_REQ_CREDIT_BUREAU_MON"].median(),inplace=True)
app_bure_prev["AMT_REQ_CREDIT_BUREAU_QRT"].fillna(app_train["AMT_REQ_CREDIT_BUREAU_QRT"].median(),inplace=True)
app_bure_prev["AMT_REQ_CREDIT_BUREAU_YEAR"].fillna(app_train["AMT_REQ_CREDIT_BUREAU_YEAR"].median(),inplace=True)
app_bure_prev["EXT_SOURCE_3"].fillna(app_train["EXT_SOURCE_3"].median(),inplace=True)
app_bure_prev["OWN_CAR_AGE"].fillna(app_train["OWN_CAR_AGE"].median(),inplace=True)


for col in app_bure_prev.columns:
    print(col,app_bure_prev[col].isnull().sum())

SK_ID_CURR 0
TARGET 0
NAME_CONTRACT_TYPE 0
CODE_GENDER 0
FLAG_OWN_CAR 0
FLAG_OWN_REALTY 0
CNT_CHILDREN 0
AMT_INCOME_TOTAL 0
AMT_CREDIT 0
AMT_ANNUITY 0
AMT_GOODS_PRICE 0
NAME_TYPE_SUITE 0
NAME_INCOME_TYPE 0
NAME_EDUCATION_TYPE 0
NAME_FAMILY_STATUS 0
NAME_HOUSING_TYPE 0
REGION_POPULATION_RELATIVE 0
DAYS_BIRTH 0
DAYS_EMPLOYED 0
DAYS_REGISTRATION 0
DAYS_ID_PUBLISH 0
OWN_CAR_AGE 0
FLAG_MOBIL 0
FLAG_EMP_PHONE 0
FLAG_WORK_PHONE 0
FLAG_CONT_MOBILE 0
FLAG_PHONE 0
FLAG_EMAIL 0
OCCUPATION_TYPE 95435
CNT_FAM_MEMBERS 0
REGION_RATING_CLIENT 0
REGION_RATING_CLIENT_W_CITY 0
WEEKDAY_APPR_PROCESS_START 0
HOUR_APPR_PROCESS_START 0
REG_REGION_NOT_LIVE_REGION 0
REG_REGION_NOT_WORK_REGION 0
LIVE_REGION_NOT_WORK_REGION 0
REG_CITY_NOT_LIVE_CITY 0
REG_CITY_NOT_WORK_CITY 0
LIVE_CITY_NOT_WORK_CITY 0
ORGANIZATION_TYPE 0
EXT_SOURCE_2 0
EXT_SOURCE_3 0
YEARS_BEGINEXPLUATATION_AVG 148686
YEARS_BEGINEXPLUATATION_MODE 148686
YEARS_BEGINEXPLUATATION_MEDI 148686
TOTALAREA_MODE 147132
EMERGENCYSTATE_MODE 144475
OBS_30_CNT_SOCIAL_CIRCLE 0
DEF_30_CNT_SOCIAL_CIRCLE 0
OBS_60_CNT_SOCIAL_CIRCLE 0
DEF_60_CNT_SOCIAL_CIRCLE 0
DAYS_LAST_PHONE_CHANGE 0
FLAG_DOCUMENT_2 0
FLAG_DOCUMENT_3 0
FLAG_DOCUMENT_4 0
FLAG_DOCUMENT_5 0
FLAG_DOCUMENT_6 0
FLAG_DOCUMENT_7 0
FLAG_DOCUMENT_8 0
FLAG_DOCUMENT_9 0
FLAG_DOCUMENT_10 0
FLAG_DOCUMENT_11 0
FLAG_DOCUMENT_12 0
FLAG_DOCUMENT_13 0
FLAG_DOCUMENT_14 0
FLAG_DOCUMENT_15 0
FLAG_DOCUMENT_16 0
FLAG_DOCUMENT_17 0
FLAG_DOCUMENT_18 0
FLAG_DOCUMENT_19 0
FLAG_DOCUMENT_20 0
FLAG_DOCUMENT_21 0
AMT_REQ_CREDIT_BUREAU_HOUR 0
AMT_REQ_CREDIT_BUREAU_DAY 0
AMT_REQ_CREDIT_BUREAU_WEEK 0
AMT_REQ_CREDIT_BUREAU_MON 0
AMT_REQ_CREDIT_BUREAU_QRT 0
AMT_REQ_CREDIT_BUREAU_YEAR 0
INCOME_GT_CREDIT_FLAG 0
CREDIT_INCOME_PERCENT 0
ANNUITY_INCOME_PERCENT 0
CREDIT_TERM 0
DAYS_EMPLOYED_PERCENT 0
BUREAU_DAYS_CREDIT 0
BUREAU_CREDIT_DAY_OVERDUE 0
BUREAU_DAYS_CREDIT_ENDDATE 0
BUREAU_DAYS_ENDDATE_FACT 0
BUREAU_AMT_CREDIT_MAX_OVERDUE 0
BUREAU_CNT_CREDIT_PROLONG 0
BUREAU_AMT_CREDIT_SUM 0
BUREAU_AMT_CREDIT_SUM_DEBT 0
BUREAU_AMT_CREDIT_SUM_LIMIT 0
BUREAU_AMT_CREDIT_SUM_OVERDUE 0
BUREAU_DAYS_CREDIT_UPDATE 0
BUREAU_AMT_ANNUITY 0
BUREAU_CREDIT_ACTIVE_Active 0
BUREAU_CREDIT_ACTIVE_Bad debt 0
BUREAU_CREDIT_ACTIVE_Closed 0
BUREAU_CREDIT_ACTIVE_Sold 0
BUREAU_CREDIT_CURRENCY_currency 1 0
BUREAU_CREDIT_CURRENCY_currency 2 0
BUREAU_CREDIT_CURRENCY_currency 3 0
BUREAU_CREDIT_CURRENCY_currency 4 0
BUREAU_CREDIT_TYPE_Another type of loan 0
BUREAU_CREDIT_TYPE_Car loan 0
BUREAU_CREDIT_TYPE_Cash loan (non-earmarked) 0
BUREAU_CREDIT_TYPE_Consumer credit 0
BUREAU_CREDIT_TYPE_Credit card 0
BUREAU_CREDIT_TYPE_Interbank credit 0
BUREAU_CREDIT_TYPE_Loan for business development 0
BUREAU_CREDIT_TYPE_Loan for purchase of shares (margin lending) 0
BUREAU_CREDIT_TYPE_Loan for the purchase of equipment 0
BUREAU_CREDIT_TYPE_Loan for working capital replenishment 0
BUREAU_CREDIT_TYPE_Microloan 0
BUREAU_CREDIT_TYPE_Mobile operator loan 0
BUREAU_CREDIT_TYPE_Mortgage 0
BUREAU_CREDIT_TYPE_Real estate loan 0
BUREAU_CREDIT_TYPE_Unknown type of loan 0
PREV_APP_COUNT 0
PREV_AMT_ANNUITY 0
PREV_AMT_APPLICATION 0
PREV_AMT_CREDIT 0
PREV_AMT_DOWN_PAYMENT 0
PREV_AMT_GOODS_PRICE 0
PREV_HOUR_APPR_PROCESS_START 0
PREV_NFLAG_LAST_APPL_IN_DAY 0
PREV_RATE_DOWN_PAYMENT 0
PREV_RATE_INTEREST_PRIMARY 0
PREV_RATE_INTEREST_PRIVILEGED 0
PREV_DAYS_DECISION 0
PREV_SELLERPLACE_AREA 0
PREV_CNT_PAYMENT 0
PREV_DAYS_FIRST_DRAWING 0
PREV_DAYS_FIRST_DUE 0
PREV_DAYS_LAST_DUE_1ST_VERSION 0
PREV_DAYS_LAST_DUE 0
PREV_DAYS_TERMINATION 0
PREV_NFLAG_INSURED_ON_APPROVAL 0
PREV_NAME_CONTRACT_TYPE_Cash loans 0
PREV_NAME_CONTRACT_TYPE_Consumer loans 0
PREV_NAME_CONTRACT_TYPE_Revolving loans 0
PREV_NAME_CONTRACT_TYPE_XNA 0
PREV_WEEKDAY_APPR_PROCESS_START_FRIDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_MONDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_SATURDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_SUNDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_THURSDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_TUESDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_WEDNESDAY 0
PREV_FLAG_LAST_APPL_PER_CONTRACT_N 0
PREV_FLAG_LAST_APPL_PER_CONTRACT_Y 0
PREV_NAME_CASH_LOAN_PURPOSE_Building a house or an annex 0
PREV_NAME_CASH_LOAN_PURPOSE_Business development 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a garage 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a holiday home / land 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a home 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a new car 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a used car 0
PREV_NAME_CASH_LOAN_PURPOSE_Car repairs 0
PREV_NAME_CASH_LOAN_PURPOSE_Education 0
PREV_NAME_CASH_LOAN_PURPOSE_Everyday expenses 0
PREV_NAME_CASH_LOAN_PURPOSE_Furniture 0
PREV_NAME_CASH_LOAN_PURPOSE_Gasification / water supply 0
PREV_NAME_CASH_LOAN_PURPOSE_Hobby 0
PREV_NAME_CASH_LOAN_PURPOSE_Journey 0
PREV_NAME_CASH_LOAN_PURPOSE_Medicine 0
PREV_NAME_CASH_LOAN_PURPOSE_Money for a third person 0
PREV_NAME_CASH_LOAN_PURPOSE_Other 0
PREV_NAME_CASH_LOAN_PURPOSE_Payments on other loans 0
PREV_NAME_CASH_LOAN_PURPOSE_Purchase of electronic equipment 0
PREV_NAME_CASH_LOAN_PURPOSE_Refusal to name the goal 0
PREV_NAME_CASH_LOAN_PURPOSE_Repairs 0
PREV_NAME_CASH_LOAN_PURPOSE_Urgent needs 0
PREV_NAME_CASH_LOAN_PURPOSE_Wedding / gift / holiday 0
PREV_NAME_CASH_LOAN_PURPOSE_XAP 0
PREV_NAME_CASH_LOAN_PURPOSE_XNA 0
PREV_NAME_CONTRACT_STATUS_Approved 0
PREV_NAME_CONTRACT_STATUS_Canceled 0
PREV_NAME_CONTRACT_STATUS_Refused 0
PREV_NAME_CONTRACT_STATUS_Unused offer 0
PREV_NAME_PAYMENT_TYPE_Cash through the bank 0
PREV_NAME_PAYMENT_TYPE_Cashless from the account of the employer 0
PREV_NAME_PAYMENT_TYPE_Non-cash from your account 0
PREV_NAME_PAYMENT_TYPE_XNA 0
PREV_CODE_REJECT_REASON_CLIENT 0
PREV_CODE_REJECT_REASON_HC 0
PREV_CODE_REJECT_REASON_LIMIT 0
PREV_CODE_REJECT_REASON_SCO 0
PREV_CODE_REJECT_REASON_SCOFR 0
PREV_CODE_REJECT_REASON_SYSTEM 0
PREV_CODE_REJECT_REASON_VERIF 0
PREV_CODE_REJECT_REASON_XAP 0
PREV_CODE_REJECT_REASON_XNA 0
PREV_NAME_TYPE_SUITE_Children 0
PREV_NAME_TYPE_SUITE_Family 0
PREV_NAME_TYPE_SUITE_Group of people 0
PREV_NAME_TYPE_SUITE_Other_A 0
PREV_NAME_TYPE_SUITE_Other_B 0
PREV_NAME_TYPE_SUITE_Spouse, partner 0
PREV_NAME_TYPE_SUITE_Unaccompanied 0
PREV_NAME_CLIENT_TYPE_New 0
PREV_NAME_CLIENT_TYPE_Refreshed 0
PREV_NAME_CLIENT_TYPE_Repeater 0
PREV_NAME_CLIENT_TYPE_XNA 0
PREV_NAME_GOODS_CATEGORY_Additional Service 0
PREV_NAME_GOODS_CATEGORY_Animals 0
PREV_NAME_GOODS_CATEGORY_Audio/Video 0
PREV_NAME_GOODS_CATEGORY_Auto Accessories 0
PREV_NAME_GOODS_CATEGORY_Clothing and Accessories 0
PREV_NAME_GOODS_CATEGORY_Computers 0
PREV_NAME_GOODS_CATEGORY_Construction Materials 0
PREV_NAME_GOODS_CATEGORY_Consumer Electronics 0
PREV_NAME_GOODS_CATEGORY_Direct Sales 0
PREV_NAME_GOODS_CATEGORY_Education 0
PREV_NAME_GOODS_CATEGORY_Fitness 0
PREV_NAME_GOODS_CATEGORY_Furniture 0
PREV_NAME_GOODS_CATEGORY_Gardening 0
PREV_NAME_GOODS_CATEGORY_Homewares 0
PREV_NAME_GOODS_CATEGORY_House Construction 0
PREV_NAME_GOODS_CATEGORY_Insurance 0
PREV_NAME_GOODS_CATEGORY_Jewelry 0
PREV_NAME_GOODS_CATEGORY_Medical Supplies 0
PREV_NAME_GOODS_CATEGORY_Medicine 0
PREV_NAME_GOODS_CATEGORY_Mobile 0
PREV_NAME_GOODS_CATEGORY_Office Appliances 0
PREV_NAME_GOODS_CATEGORY_Other 0
PREV_NAME_GOODS_CATEGORY_Photo / Cinema Equipment 0
PREV_NAME_GOODS_CATEGORY_Sport and Leisure 0
PREV_NAME_GOODS_CATEGORY_Tourism 0
PREV_NAME_GOODS_CATEGORY_Vehicles 0
PREV_NAME_GOODS_CATEGORY_Weapon 0
PREV_NAME_GOODS_CATEGORY_XNA 0
PREV_NAME_PORTFOLIO_Cards 0
PREV_NAME_PORTFOLIO_Cars 0
PREV_NAME_PORTFOLIO_Cash 0
PREV_NAME_PORTFOLIO_POS 0
PREV_NAME_PORTFOLIO_XNA 0
PREV_NAME_PRODUCT_TYPE_XNA 0
PREV_NAME_PRODUCT_TYPE_walk-in 0
PREV_NAME_PRODUCT_TYPE_x-sell 0
PREV_CHANNEL_TYPE_AP+ (Cash loan) 0
PREV_CHANNEL_TYPE_Car dealer 0
PREV_CHANNEL_TYPE_Channel of corporate sales 0
PREV_CHANNEL_TYPE_Contact center 0
PREV_CHANNEL_TYPE_Country-wide 0
PREV_CHANNEL_TYPE_Credit and cash offices 0
PREV_CHANNEL_TYPE_Regional / Local 0
PREV_CHANNEL_TYPE_Stone 0
PREV_NAME_SELLER_INDUSTRY_Auto technology 0
PREV_NAME_SELLER_INDUSTRY_Clothing 0
PREV_NAME_SELLER_INDUSTRY_Connectivity 0
PREV_NAME_SELLER_INDUSTRY_Construction 0
PREV_NAME_SELLER_INDUSTRY_Consumer electronics 0
PREV_NAME_SELLER_INDUSTRY_Furniture 0
PREV_NAME_SELLER_INDUSTRY_Industry 0
PREV_NAME_SELLER_INDUSTRY_Jewelry 0
PREV_NAME_SELLER_INDUSTRY_MLM partners 0
PREV_NAME_SELLER_INDUSTRY_Tourism 0
PREV_NAME_SELLER_INDUSTRY_XNA 0
PREV_NAME_YIELD_GROUP_XNA 0
PREV_NAME_YIELD_GROUP_high 0
PREV_NAME_YIELD_GROUP_low_action 0
PREV_NAME_YIELD_GROUP_low_normal 0
PREV_NAME_YIELD_GROUP_middle 0
PREV_PRODUCT_COMBINATION_Card Street 0
PREV_PRODUCT_COMBINATION_Card X-Sell 0
PREV_PRODUCT_COMBINATION_Cash 0
PREV_PRODUCT_COMBINATION_Cash Street: high 0
PREV_PRODUCT_COMBINATION_Cash Street: low 0
PREV_PRODUCT_COMBINATION_Cash Street: middle 0
PREV_PRODUCT_COMBINATION_Cash X-Sell: high 0
PREV_PRODUCT_COMBINATION_Cash X-Sell: low 0
PREV_PRODUCT_COMBINATION_Cash X-Sell: middle 0
PREV_PRODUCT_COMBINATION_POS household with interest 0
PREV_PRODUCT_COMBINATION_POS household without interest 0
PREV_PRODUCT_COMBINATION_POS industry with interest 0
PREV_PRODUCT_COMBINATION_POS industry without interest 0
PREV_PRODUCT_COMBINATION_POS mobile with interest 0
PREV_PRODUCT_COMBINATION_POS mobile without interest 0
PREV_PRODUCT_COMBINATION_POS other with interest 0
PREV_PRODUCT_COMBINATION_POS others without interest 0
POS_MONTHS_BALANCE 0
POS_CNT_INSTALMENT 0
POS_CNT_INSTALMENT_FUTURE 0
POS_SK_DPD 0
POS_SK_DPD_DEF 0
POS_NAME_CONTRACT_STATUS_Active 0
POS_NAME_CONTRACT_STATUS_Amortized debt 0
POS_NAME_CONTRACT_STATUS_Approved 0
POS_NAME_CONTRACT_STATUS_Canceled 0
POS_NAME_CONTRACT_STATUS_Completed 0
POS_NAME_CONTRACT_STATUS_Demand 0
POS_NAME_CONTRACT_STATUS_Returned to the store 0
POS_NAME_CONTRACT_STATUS_Signed 0
POS_NAME_CONTRACT_STATUS_XNA 0
INSTA_NUM_INSTALMENT_VERSION 0
INSTA_NUM_INSTALMENT_NUMBER 0
INSTA_DAYS_INSTALMENT 0
INSTA_DAYS_ENTRY_PAYMENT 0
INSTA_AMT_INSTALMENT 0
INSTA_AMT_PAYMENT 0
CREDIT_MONTHS_BALANCE 0
CREDIT_AMT_BALANCE 0
CREDIT_AMT_CREDIT_LIMIT_ACTUAL 0
CREDIT_AMT_DRAWINGS_ATM_CURRENT 0
CREDIT_AMT_DRAWINGS_CURRENT 0
CREDIT_AMT_DRAWINGS_OTHER_CURRENT 0
CREDIT_AMT_DRAWINGS_POS_CURRENT 0
CREDIT_AMT_INST_MIN_REGULARITY 0
CREDIT_AMT_PAYMENT_CURRENT 0
CREDIT_AMT_PAYMENT_TOTAL_CURRENT 0
CREDIT_AMT_RECEIVABLE_PRINCIPAL 0
CREDIT_AMT_RECIVABLE 0
CREDIT_AMT_TOTAL_RECEIVABLE 0
CREDIT_CNT_DRAWINGS_ATM_CURRENT 0
CREDIT_CNT_DRAWINGS_CURRENT 0
CREDIT_CNT_DRAWINGS_OTHER_CURRENT 0
CREDIT_CNT_DRAWINGS_POS_CURRENT 0
CREDIT_CNT_INSTALMENT_MATURE_CUM 0
CREDIT_SK_DPD 0
CREDIT_SK_DPD_DEF 0
CREDIT_NAME_CONTRACT_STATUS_Active 0
CREDIT_NAME_CONTRACT_STATUS_Approved 0
CREDIT_NAME_CONTRACT_STATUS_Completed 0
CREDIT_NAME_CONTRACT_STATUS_Demand 0
CREDIT_NAME_CONTRACT_STATUS_Refused 0
CREDIT_NAME_CONTRACT_STATUS_Sent proposal 0
CREDIT_NAME_CONTRACT_STATUS_Signed 0


app_bure_prev["YEARS_BEGINEXPLUATATION_AVG"].fillna(app_bure_prev["YEARS_BEGINEXPLUATATION_AVG"].mode()[0],inplace=True)
app_bure_prev["YEARS_BEGINEXPLUATATION_MODE"].fillna(app_bure_prev["YEARS_BEGINEXPLUATATION_MODE"].mode()[0],inplace=True)
app_bure_prev["YEARS_BEGINEXPLUATATION_MEDI"].fillna(app_bure_prev["YEARS_BEGINEXPLUATATION_MEDI"].mode()[0],inplace=True)
app_bure_prev["TOTALAREA_MODE"].fillna(app_bure_prev["TOTALAREA_MODE"].mode()[0],inplace=True)
app_bure_prev["OCCUPATION_TYPE"].fillna(app_bure_prev["OCCUPATION_TYPE"].mode()[0],inplace=True)
app_bure_prev["EMERGENCYSTATE_MODE"].fillna(app_bure_prev["EMERGENCYSTATE_MODE"].mode()[0],inplace=True)


for col in app_bure_prev.columns:
    print(col,app_bure_prev[col].isnull().sum())

SK_ID_CURR 0
TARGET 0
NAME_CONTRACT_TYPE 0
CODE_GENDER 0
FLAG_OWN_CAR 0
FLAG_OWN_REALTY 0
CNT_CHILDREN 0
AMT_INCOME_TOTAL 0
AMT_CREDIT 0
AMT_ANNUITY 0
AMT_GOODS_PRICE 0
NAME_TYPE_SUITE 0
NAME_INCOME_TYPE 0
NAME_EDUCATION_TYPE 0
NAME_FAMILY_STATUS 0
NAME_HOUSING_TYPE 0
REGION_POPULATION_RELATIVE 0
DAYS_BIRTH 0
DAYS_EMPLOYED 0
DAYS_REGISTRATION 0
DAYS_ID_PUBLISH 0
OWN_CAR_AGE 0
FLAG_MOBIL 0
FLAG_EMP_PHONE 0
FLAG_WORK_PHONE 0
FLAG_CONT_MOBILE 0
FLAG_PHONE 0
FLAG_EMAIL 0
OCCUPATION_TYPE 0
CNT_FAM_MEMBERS 0
REGION_RATING_CLIENT 0
REGION_RATING_CLIENT_W_CITY 0
WEEKDAY_APPR_PROCESS_START 0
HOUR_APPR_PROCESS_START 0
REG_REGION_NOT_LIVE_REGION 0
REG_REGION_NOT_WORK_REGION 0
LIVE_REGION_NOT_WORK_REGION 0
REG_CITY_NOT_LIVE_CITY 0
REG_CITY_NOT_WORK_CITY 0
LIVE_CITY_NOT_WORK_CITY 0
ORGANIZATION_TYPE 0
EXT_SOURCE_2 0
EXT_SOURCE_3 0
YEARS_BEGINEXPLUATATION_AVG 0
YEARS_BEGINEXPLUATATION_MODE 0
YEARS_BEGINEXPLUATATION_MEDI 0
TOTALAREA_MODE 0
EMERGENCYSTATE_MODE 0
OBS_30_CNT_SOCIAL_CIRCLE 0
DEF_30_CNT_SOCIAL_CIRCLE 0
OBS_60_CNT_SOCIAL_CIRCLE 0
DEF_60_CNT_SOCIAL_CIRCLE 0
DAYS_LAST_PHONE_CHANGE 0
FLAG_DOCUMENT_2 0
FLAG_DOCUMENT_3 0
FLAG_DOCUMENT_4 0
FLAG_DOCUMENT_5 0
FLAG_DOCUMENT_6 0
FLAG_DOCUMENT_7 0
FLAG_DOCUMENT_8 0
FLAG_DOCUMENT_9 0
FLAG_DOCUMENT_10 0
FLAG_DOCUMENT_11 0
FLAG_DOCUMENT_12 0
FLAG_DOCUMENT_13 0
FLAG_DOCUMENT_14 0
FLAG_DOCUMENT_15 0
FLAG_DOCUMENT_16 0
FLAG_DOCUMENT_17 0
FLAG_DOCUMENT_18 0
FLAG_DOCUMENT_19 0
FLAG_DOCUMENT_20 0
FLAG_DOCUMENT_21 0
AMT_REQ_CREDIT_BUREAU_HOUR 0
AMT_REQ_CREDIT_BUREAU_DAY 0
AMT_REQ_CREDIT_BUREAU_WEEK 0
AMT_REQ_CREDIT_BUREAU_MON 0
AMT_REQ_CREDIT_BUREAU_QRT 0
AMT_REQ_CREDIT_BUREAU_YEAR 0
INCOME_GT_CREDIT_FLAG 0
CREDIT_INCOME_PERCENT 0
ANNUITY_INCOME_PERCENT 0
CREDIT_TERM 0
DAYS_EMPLOYED_PERCENT 0
BUREAU_DAYS_CREDIT 0
BUREAU_CREDIT_DAY_OVERDUE 0
BUREAU_DAYS_CREDIT_ENDDATE 0
BUREAU_DAYS_ENDDATE_FACT 0
BUREAU_AMT_CREDIT_MAX_OVERDUE 0
BUREAU_CNT_CREDIT_PROLONG 0
BUREAU_AMT_CREDIT_SUM 0
BUREAU_AMT_CREDIT_SUM_DEBT 0
BUREAU_AMT_CREDIT_SUM_LIMIT 0
BUREAU_AMT_CREDIT_SUM_OVERDUE 0
BUREAU_DAYS_CREDIT_UPDATE 0
BUREAU_AMT_ANNUITY 0
BUREAU_CREDIT_ACTIVE_Active 0
BUREAU_CREDIT_ACTIVE_Bad debt 0
BUREAU_CREDIT_ACTIVE_Closed 0
BUREAU_CREDIT_ACTIVE_Sold 0
BUREAU_CREDIT_CURRENCY_currency 1 0
BUREAU_CREDIT_CURRENCY_currency 2 0
BUREAU_CREDIT_CURRENCY_currency 3 0
BUREAU_CREDIT_CURRENCY_currency 4 0
BUREAU_CREDIT_TYPE_Another type of loan 0
BUREAU_CREDIT_TYPE_Car loan 0
BUREAU_CREDIT_TYPE_Cash loan (non-earmarked) 0
BUREAU_CREDIT_TYPE_Consumer credit 0
BUREAU_CREDIT_TYPE_Credit card 0
BUREAU_CREDIT_TYPE_Interbank credit 0
BUREAU_CREDIT_TYPE_Loan for business development 0
BUREAU_CREDIT_TYPE_Loan for purchase of shares (margin lending) 0
BUREAU_CREDIT_TYPE_Loan for the purchase of equipment 0
BUREAU_CREDIT_TYPE_Loan for working capital replenishment 0
BUREAU_CREDIT_TYPE_Microloan 0
BUREAU_CREDIT_TYPE_Mobile operator loan 0
BUREAU_CREDIT_TYPE_Mortgage 0
BUREAU_CREDIT_TYPE_Real estate loan 0
BUREAU_CREDIT_TYPE_Unknown type of loan 0
PREV_APP_COUNT 0
PREV_AMT_ANNUITY 0
PREV_AMT_APPLICATION 0
PREV_AMT_CREDIT 0
PREV_AMT_DOWN_PAYMENT 0
PREV_AMT_GOODS_PRICE 0
PREV_HOUR_APPR_PROCESS_START 0
PREV_NFLAG_LAST_APPL_IN_DAY 0
PREV_RATE_DOWN_PAYMENT 0
PREV_RATE_INTEREST_PRIMARY 0
PREV_RATE_INTEREST_PRIVILEGED 0
PREV_DAYS_DECISION 0
PREV_SELLERPLACE_AREA 0
PREV_CNT_PAYMENT 0
PREV_DAYS_FIRST_DRAWING 0
PREV_DAYS_FIRST_DUE 0
PREV_DAYS_LAST_DUE_1ST_VERSION 0
PREV_DAYS_LAST_DUE 0
PREV_DAYS_TERMINATION 0
PREV_NFLAG_INSURED_ON_APPROVAL 0
PREV_NAME_CONTRACT_TYPE_Cash loans 0
PREV_NAME_CONTRACT_TYPE_Consumer loans 0
PREV_NAME_CONTRACT_TYPE_Revolving loans 0
PREV_NAME_CONTRACT_TYPE_XNA 0
PREV_WEEKDAY_APPR_PROCESS_START_FRIDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_MONDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_SATURDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_SUNDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_THURSDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_TUESDAY 0
PREV_WEEKDAY_APPR_PROCESS_START_WEDNESDAY 0
PREV_FLAG_LAST_APPL_PER_CONTRACT_N 0
PREV_FLAG_LAST_APPL_PER_CONTRACT_Y 0
PREV_NAME_CASH_LOAN_PURPOSE_Building a house or an annex 0
PREV_NAME_CASH_LOAN_PURPOSE_Business development 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a garage 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a holiday home / land 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a home 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a new car 0
PREV_NAME_CASH_LOAN_PURPOSE_Buying a used car 0
PREV_NAME_CASH_LOAN_PURPOSE_Car repairs 0
PREV_NAME_CASH_LOAN_PURPOSE_Education 0
PREV_NAME_CASH_LOAN_PURPOSE_Everyday expenses 0
PREV_NAME_CASH_LOAN_PURPOSE_Furniture 0
PREV_NAME_CASH_LOAN_PURPOSE_Gasification / water supply 0
PREV_NAME_CASH_LOAN_PURPOSE_Hobby 0
PREV_NAME_CASH_LOAN_PURPOSE_Journey 0
PREV_NAME_CASH_LOAN_PURPOSE_Medicine 0
PREV_NAME_CASH_LOAN_PURPOSE_Money for a third person 0
PREV_NAME_CASH_LOAN_PURPOSE_Other 0
PREV_NAME_CASH_LOAN_PURPOSE_Payments on other loans 0
PREV_NAME_CASH_LOAN_PURPOSE_Purchase of electronic equipment 0
PREV_NAME_CASH_LOAN_PURPOSE_Refusal to name the goal 0
PREV_NAME_CASH_LOAN_PURPOSE_Repairs 0
PREV_NAME_CASH_LOAN_PURPOSE_Urgent needs 0
PREV_NAME_CASH_LOAN_PURPOSE_Wedding / gift / holiday 0
PREV_NAME_CASH_LOAN_PURPOSE_XAP 0
PREV_NAME_CASH_LOAN_PURPOSE_XNA 0
PREV_NAME_CONTRACT_STATUS_Approved 0
PREV_NAME_CONTRACT_STATUS_Canceled 0
PREV_NAME_CONTRACT_STATUS_Refused 0
PREV_NAME_CONTRACT_STATUS_Unused offer 0
PREV_NAME_PAYMENT_TYPE_Cash through the bank 0
PREV_NAME_PAYMENT_TYPE_Cashless from the account of the employer 0
PREV_NAME_PAYMENT_TYPE_Non-cash from your account 0
PREV_NAME_PAYMENT_TYPE_XNA 0
PREV_CODE_REJECT_REASON_CLIENT 0
PREV_CODE_REJECT_REASON_HC 0
PREV_CODE_REJECT_REASON_LIMIT 0
PREV_CODE_REJECT_REASON_SCO 0
PREV_CODE_REJECT_REASON_SCOFR 0
PREV_CODE_REJECT_REASON_SYSTEM 0
PREV_CODE_REJECT_REASON_VERIF 0
PREV_CODE_REJECT_REASON_XAP 0
PREV_CODE_REJECT_REASON_XNA 0
PREV_NAME_TYPE_SUITE_Children 0
PREV_NAME_TYPE_SUITE_Family 0
PREV_NAME_TYPE_SUITE_Group of people 0
PREV_NAME_TYPE_SUITE_Other_A 0
PREV_NAME_TYPE_SUITE_Other_B 0
PREV_NAME_TYPE_SUITE_Spouse, partner 0
PREV_NAME_TYPE_SUITE_Unaccompanied 0
PREV_NAME_CLIENT_TYPE_New 0
PREV_NAME_CLIENT_TYPE_Refreshed 0
PREV_NAME_CLIENT_TYPE_Repeater 0
PREV_NAME_CLIENT_TYPE_XNA 0
PREV_NAME_GOODS_CATEGORY_Additional Service 0
PREV_NAME_GOODS_CATEGORY_Animals 0
PREV_NAME_GOODS_CATEGORY_Audio/Video 0
PREV_NAME_GOODS_CATEGORY_Auto Accessories 0
PREV_NAME_GOODS_CATEGORY_Clothing and Accessories 0
PREV_NAME_GOODS_CATEGORY_Computers 0
PREV_NAME_GOODS_CATEGORY_Construction Materials 0
PREV_NAME_GOODS_CATEGORY_Consumer Electronics 0
PREV_NAME_GOODS_CATEGORY_Direct Sales 0
PREV_NAME_GOODS_CATEGORY_Education 0
PREV_NAME_GOODS_CATEGORY_Fitness 0
PREV_NAME_GOODS_CATEGORY_Furniture 0
PREV_NAME_GOODS_CATEGORY_Gardening 0
PREV_NAME_GOODS_CATEGORY_Homewares 0
PREV_NAME_GOODS_CATEGORY_House Construction 0
PREV_NAME_GOODS_CATEGORY_Insurance 0
PREV_NAME_GOODS_CATEGORY_Jewelry 0
PREV_NAME_GOODS_CATEGORY_Medical Supplies 0
PREV_NAME_GOODS_CATEGORY_Medicine 0
PREV_NAME_GOODS_CATEGORY_Mobile 0
PREV_NAME_GOODS_CATEGORY_Office Appliances 0
PREV_NAME_GOODS_CATEGORY_Other 0
PREV_NAME_GOODS_CATEGORY_Photo / Cinema Equipment 0
PREV_NAME_GOODS_CATEGORY_Sport and Leisure 0
PREV_NAME_GOODS_CATEGORY_Tourism 0
PREV_NAME_GOODS_CATEGORY_Vehicles 0
PREV_NAME_GOODS_CATEGORY_Weapon 0
PREV_NAME_GOODS_CATEGORY_XNA 0
PREV_NAME_PORTFOLIO_Cards 0
PREV_NAME_PORTFOLIO_Cars 0
PREV_NAME_PORTFOLIO_Cash 0
PREV_NAME_PORTFOLIO_POS 0
PREV_NAME_PORTFOLIO_XNA 0
PREV_NAME_PRODUCT_TYPE_XNA 0
PREV_NAME_PRODUCT_TYPE_walk-in 0
PREV_NAME_PRODUCT_TYPE_x-sell 0
PREV_CHANNEL_TYPE_AP+ (Cash loan) 0
PREV_CHANNEL_TYPE_Car dealer 0
PREV_CHANNEL_TYPE_Channel of corporate sales 0
PREV_CHANNEL_TYPE_Contact center 0
PREV_CHANNEL_TYPE_Country-wide 0
PREV_CHANNEL_TYPE_Credit and cash offices 0
PREV_CHANNEL_TYPE_Regional / Local 0
PREV_CHANNEL_TYPE_Stone 0
PREV_NAME_SELLER_INDUSTRY_Auto technology 0
PREV_NAME_SELLER_INDUSTRY_Clothing 0
PREV_NAME_SELLER_INDUSTRY_Connectivity 0
PREV_NAME_SELLER_INDUSTRY_Construction 0
PREV_NAME_SELLER_INDUSTRY_Consumer electronics 0
PREV_NAME_SELLER_INDUSTRY_Furniture 0
PREV_NAME_SELLER_INDUSTRY_Industry 0
PREV_NAME_SELLER_INDUSTRY_Jewelry 0
PREV_NAME_SELLER_INDUSTRY_MLM partners 0
PREV_NAME_SELLER_INDUSTRY_Tourism 0
PREV_NAME_SELLER_INDUSTRY_XNA 0
PREV_NAME_YIELD_GROUP_XNA 0
PREV_NAME_YIELD_GROUP_high 0
PREV_NAME_YIELD_GROUP_low_action 0
PREV_NAME_YIELD_GROUP_low_normal 0
PREV_NAME_YIELD_GROUP_middle 0
PREV_PRODUCT_COMBINATION_Card Street 0
PREV_PRODUCT_COMBINATION_Card X-Sell 0
PREV_PRODUCT_COMBINATION_Cash 0
PREV_PRODUCT_COMBINATION_Cash Street: high 0
PREV_PRODUCT_COMBINATION_Cash Street: low 0
PREV_PRODUCT_COMBINATION_Cash Street: middle 0
PREV_PRODUCT_COMBINATION_Cash X-Sell: high 0
PREV_PRODUCT_COMBINATION_Cash X-Sell: low 0
PREV_PRODUCT_COMBINATION_Cash X-Sell: middle 0
PREV_PRODUCT_COMBINATION_POS household with interest 0
PREV_PRODUCT_COMBINATION_POS household without interest 0
PREV_PRODUCT_COMBINATION_POS industry with interest 0
PREV_PRODUCT_COMBINATION_POS industry without interest 0
PREV_PRODUCT_COMBINATION_POS mobile with interest 0
PREV_PRODUCT_COMBINATION_POS mobile without interest 0
PREV_PRODUCT_COMBINATION_POS other with interest 0
PREV_PRODUCT_COMBINATION_POS others without interest 0
POS_MONTHS_BALANCE 0
POS_CNT_INSTALMENT 0
POS_CNT_INSTALMENT_FUTURE 0
POS_SK_DPD 0
POS_SK_DPD_DEF 0
POS_NAME_CONTRACT_STATUS_Active 0
POS_NAME_CONTRACT_STATUS_Amortized debt 0
POS_NAME_CONTRACT_STATUS_Approved 0
POS_NAME_CONTRACT_STATUS_Canceled 0
POS_NAME_CONTRACT_STATUS_Completed 0
POS_NAME_CONTRACT_STATUS_Demand 0
POS_NAME_CONTRACT_STATUS_Returned to the store 0
POS_NAME_CONTRACT_STATUS_Signed 0
POS_NAME_CONTRACT_STATUS_XNA 0
INSTA_NUM_INSTALMENT_VERSION 0
INSTA_NUM_INSTALMENT_NUMBER 0
INSTA_DAYS_INSTALMENT 0
INSTA_DAYS_ENTRY_PAYMENT 0
INSTA_AMT_INSTALMENT 0
INSTA_AMT_PAYMENT 0
CREDIT_MONTHS_BALANCE 0
CREDIT_AMT_BALANCE 0
CREDIT_AMT_CREDIT_LIMIT_ACTUAL 0
CREDIT_AMT_DRAWINGS_ATM_CURRENT 0
CREDIT_AMT_DRAWINGS_CURRENT 0
CREDIT_AMT_DRAWINGS_OTHER_CURRENT 0
CREDIT_AMT_DRAWINGS_POS_CURRENT 0
CREDIT_AMT_INST_MIN_REGULARITY 0
CREDIT_AMT_PAYMENT_CURRENT 0
CREDIT_AMT_PAYMENT_TOTAL_CURRENT 0
CREDIT_AMT_RECEIVABLE_PRINCIPAL 0
CREDIT_AMT_RECIVABLE 0
CREDIT_AMT_TOTAL_RECEIVABLE 0
CREDIT_CNT_DRAWINGS_ATM_CURRENT 0
CREDIT_CNT_DRAWINGS_CURRENT 0
CREDIT_CNT_DRAWINGS_OTHER_CURRENT 0
CREDIT_CNT_DRAWINGS_POS_CURRENT 0
CREDIT_CNT_INSTALMENT_MATURE_CUM 0
CREDIT_SK_DPD 0
CREDIT_SK_DPD_DEF 0
CREDIT_NAME_CONTRACT_STATUS_Active 0
CREDIT_NAME_CONTRACT_STATUS_Approved 0
CREDIT_NAME_CONTRACT_STATUS_Completed 0
CREDIT_NAME_CONTRACT_STATUS_Demand 0
CREDIT_NAME_CONTRACT_STATUS_Refused 0
CREDIT_NAME_CONTRACT_STATUS_Sent proposal 0
CREDIT_NAME_CONTRACT_STATUS_Signed 0


app_bure_prev


# Identify the categorical columns
categorical_columns = app_bure_prev.select_dtypes(include=['object']).columns

# Print the categorical columns
print(categorical_columns)

Index(['NAME_CONTRACT_TYPE', 'CODE_GENDER', 'FLAG_OWN_CAR', 'FLAG_OWN_REALTY',
       'NAME_TYPE_SUITE', 'NAME_INCOME_TYPE', 'NAME_EDUCATION_TYPE',
       'NAME_FAMILY_STATUS', 'NAME_HOUSING_TYPE', 'OCCUPATION_TYPE',
       'WEEKDAY_APPR_PROCESS_START', 'ORGANIZATION_TYPE',
       'EMERGENCYSTATE_MODE'],
      dtype='object')


app_bure_prev.value_counts('INCOME_GT_CREDIT_FLAG')

INCOME_GT_CREDIT_FLAG
False    290440
True      14091
dtype: int64


for i in ['NAME_CONTRACT_TYPE', 'CODE_GENDER', 'FLAG_OWN_CAR', 'FLAG_OWN_REALTY',
       'NAME_TYPE_SUITE', 'NAME_INCOME_TYPE', 'NAME_EDUCATION_TYPE',
       'NAME_FAMILY_STATUS', 'NAME_HOUSING_TYPE', 'OCCUPATION_TYPE',
       'WEEKDAY_APPR_PROCESS_START', 'ORGANIZATION_TYPE',
       'EMERGENCYSTATE_MODE','INCOME_GT_CREDIT_FLAG']:
    print(i, app_bure_prev[i].unique())
    print('-------------------------------------------------------------------')

NAME_CONTRACT_TYPE ['Cash loans' 'Revolving loans']
-------------------------------------------------------------------
CODE_GENDER ['M' 'F' 'XNA']
-------------------------------------------------------------------
FLAG_OWN_CAR ['N' 'Y']
-------------------------------------------------------------------
FLAG_OWN_REALTY ['Y' 'N']
-------------------------------------------------------------------
NAME_TYPE_SUITE ['Unaccompanied' 'Family' 'Spouse, partner' 'Children' 'Other_A' 'Other_B'
 'Group of people']
-------------------------------------------------------------------
NAME_INCOME_TYPE ['Working' 'State servant' 'Commercial associate' 'Pensioner' 'Unemployed'
 'Student' 'Businessman' 'Maternity leave']
-------------------------------------------------------------------
NAME_EDUCATION_TYPE ['Secondary / secondary special' 'Higher education' 'Incomplete higher'
 'Lower secondary' 'Academic degree']
-------------------------------------------------------------------
NAME_FAMILY_STATUS ['Single / not married' 'Married' 'Civil marriage' 'Widow' 'Separated']
-------------------------------------------------------------------
NAME_HOUSING_TYPE ['House / apartment' 'Rented apartment' 'With parents'
 'Municipal apartment' 'Office apartment' 'Co-op apartment']
-------------------------------------------------------------------
OCCUPATION_TYPE ['Laborers' 'Core staff' 'Accountants' 'Managers' 'Drivers' 'Sales staff'
 'Cleaning staff' 'Cooking staff' 'Private service staff' 'Medicine staff'
 'Security staff' 'High skill tech staff' 'Waiters/barmen staff'
 'Low-skill Laborers' 'Realty agents' 'Secretaries' 'IT staff' 'HR staff']
-------------------------------------------------------------------
WEEKDAY_APPR_PROCESS_START ['WEDNESDAY' 'MONDAY' 'THURSDAY' 'SUNDAY' 'SATURDAY' 'FRIDAY' 'TUESDAY']
-------------------------------------------------------------------
ORGANIZATION_TYPE ['Business Entity Type 3' 'School' 'Government' 'Religion' 'Other' 'XNA'
 'Electricity' 'Medicine' 'Business Entity Type 2' 'Self-employed'
 'Transport: type 2' 'Construction' 'Housing' 'Kindergarten'
 'Trade: type 7' 'Industry: type 11' 'Military' 'Services'
 'Security Ministries' 'Transport: type 4' 'Industry: type 1' 'Emergency'
 'Security' 'Trade: type 2' 'University' 'Police' 'Business Entity Type 1'
 'Postal' 'Transport: type 3' 'Industry: type 4' 'Agriculture'
 'Restaurant' 'Culture' 'Hotel' 'Industry: type 7' 'Trade: type 3'
 'Industry: type 3' 'Bank' 'Industry: type 9' 'Insurance' 'Trade: type 6'
 'Industry: type 2' 'Transport: type 1' 'Industry: type 12' 'Mobile'
 'Trade: type 1' 'Industry: type 5' 'Industry: type 10' 'Legal Services'
 'Advertising' 'Trade: type 5' 'Cleaning' 'Industry: type 13'
 'Trade: type 4' 'Telecom' 'Industry: type 8' 'Realtor' 'Industry: type 6']
-------------------------------------------------------------------
EMERGENCYSTATE_MODE ['No' 'Yes']
-------------------------------------------------------------------
INCOME_GT_CREDIT_FLAG [False  True]
-------------------------------------------------------------------


from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
for i in ['NAME_CONTRACT_TYPE', 'CODE_GENDER', 'FLAG_OWN_CAR', 'FLAG_OWN_REALTY',
       'NAME_TYPE_SUITE', 'NAME_INCOME_TYPE', 'NAME_EDUCATION_TYPE',
       'NAME_FAMILY_STATUS', 'NAME_HOUSING_TYPE', 'OCCUPATION_TYPE',
       'WEEKDAY_APPR_PROCESS_START', 'ORGANIZATION_TYPE',
       'EMERGENCYSTATE_MODE','INCOME_GT_CREDIT_FLAG']:
    app_bure_prev[i] = le.fit_transform(app_bure_prev[i])
app_bure_prev.head()


x=app_bure_prev.drop(['TARGET','SK_ID_CURR'],axis=1)
x.head()


y=app_bure_prev.TARGET

y

0         1
1         0
2         0
3         0
4         0
         ..
307506    0
307507    0
307508    0
307509    1
307510    0
Name: TARGET, Length: 304531, dtype: int64


from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.25,random_state=33)


y_test

134941    1
259901    0
213366    0
151480    0
290128    0
         ..
164694    0
85126     0
198511    1
64162     0
146734    0
Name: TARGET, Length: 76133, dtype: int64


x_train


x_train


y_train

51515     0
240897    0
261925    0
82413     0
214981    0
         ..
149001    0
198572    0
160464    0
226067    0
105162    0
Name: TARGET, Length: 228398, dtype: int64


y.value_counts()

0    279864
1     24667
Name: TARGET, dtype: int64


from sklearn.preprocessing import MinMaxScaler
scaler=MinMaxScaler()
scaled_data=scaler.fit_transform(x)


df=pd.DataFrame(data=scaled_data,columns=x.columns)


df.head

<bound method NDFrame.head of         NAME_CONTRACT_TYPE  CODE_GENDER  FLAG_OWN_CAR  FLAG_OWN_REALTY  \
0                      0.0          0.5           0.0              1.0   
1                      0.0          0.0           0.0              0.0   
2                      1.0          0.5           1.0              1.0   
3                      0.0          0.0           0.0              1.0   
4                      0.0          0.5           0.0              1.0   
...                    ...          ...           ...              ...   
304526                 0.0          0.5           0.0              0.0   
304527                 0.0          0.0           0.0              1.0   
304528                 0.0          0.0           0.0              1.0   
304529                 0.0          0.0           0.0              1.0   
304530                 0.0          0.0           0.0              0.0   

        CNT_CHILDREN  AMT_INCOME_TOTAL  AMT_CREDIT  AMT_ANNUITY  \
0                0.0          0.001512    0.090287     0.090032   
1                0.0          0.002089    0.311736     0.132924   
2                0.0          0.000358    0.022472     0.020025   
3                0.0          0.000935    0.066837     0.109477   
4                0.0          0.000819    0.116854     0.078975   
...              ...               ...         ...          ...   
304526           0.0          0.001127    0.052360     0.101176   
304527           0.0          0.000396    0.056067     0.040505   
304528           0.0          0.001089    0.157969     0.110618   
304529           0.0          0.001243    0.081175     0.072499   
304530           0.0          0.001127    0.157303     0.185258   

        AMT_GOODS_PRICE  NAME_TYPE_SUITE  ...  \
0              0.077441         1.000000  ...   
1              0.271605         0.166667  ...   
2              0.023569         1.000000  ...   
3              0.063973         1.000000  ...   
4              0.117845         1.000000  ...   
...                 ...              ...  ...   
304526         0.046016         1.000000  ...   
304527         0.046016         1.000000  ...   
304528         0.135802         1.000000  ...   
304529         0.069585         1.000000  ...   
304530         0.158249         1.000000  ...   

        CREDIT_CNT_INSTALMENT_MATURE_CUM  CREDIT_SK_DPD  CREDIT_SK_DPD_DEF  \
0                                    0.0            0.0                0.0   
1                                    0.0            0.0                0.0   
2                                    0.0            0.0                0.0   
3                                    0.0            0.0                0.0   
4                                    0.0            0.0                0.0   
...                                  ...            ...                ...   
304526                               0.0            0.0                0.0   
304527                               0.0            0.0                0.0   
304528                               0.0            0.0                0.0   
304529                               0.0            0.0                0.0   
304530                               0.0            0.0                0.0   

        CREDIT_NAME_CONTRACT_STATUS_Active  \
0                                      0.0   
1                                      0.0   
2                                      0.0   
3                                      1.0   
4                                      0.0   
...                                    ...   
304526                                 0.0   
304527                                 0.0   
304528                                 0.0   
304529                                 0.0   
304530                                 0.0   

        CREDIT_NAME_CONTRACT_STATUS_Approved  \
0                                        0.0   
1                                        0.0   
2                                        0.0   
3                                        0.0   
4                                        0.0   
...                                      ...   
304526                                   0.0   
304527                                   0.0   
304528                                   0.0   
304529                                   0.0   
304530                                   0.0   

        CREDIT_NAME_CONTRACT_STATUS_Completed  \
0                                         0.0   
1                                         0.0   
2                                         0.0   
3                                         0.0   
4                                         0.0   
...                                       ...   
304526                                    0.0   
304527                                    0.0   
304528                                    0.0   
304529                                    0.0   
304530                                    0.0   

        CREDIT_NAME_CONTRACT_STATUS_Demand  \
0                                      0.0   
1                                      0.0   
2                                      0.0   
3                                      0.0   
4                                      0.0   
...                                    ...   
304526                                 0.0   
304527                                 0.0   
304528                                 0.0   
304529                                 0.0   
304530                                 0.0   

        CREDIT_NAME_CONTRACT_STATUS_Refused  \
0                                       0.0   
1                                       0.0   
2                                       0.0   
3                                       0.0   
4                                       0.0   
...                                     ...   
304526                                  0.0   
304527                                  0.0   
304528                                  0.0   
304529                                  0.0   
304530                                  0.0   

        CREDIT_NAME_CONTRACT_STATUS_Sent proposal  \
0                                             0.0   
1                                             0.0   
2                                             0.0   
3                                             0.0   
4                                             0.0   
...                                           ...   
304526                                        0.0   
304527                                        0.0   
304528                                        0.0   
304529                                        0.0   
304530                                        0.0   

        CREDIT_NAME_CONTRACT_STATUS_Signed  
0                                      0.0  
1                                      0.0  
2                                      0.0  
3                                      0.0  
4                                      0.0  
...                                    ...  
304526                                 0.0  
304527                                 0.0  
304528                                 0.0  
304529                                 0.0  
304530                                 0.0  

[304531 rows x 327 columns]>


from sklearn.decomposition import PCA
pca=PCA()
principalcomponents=pca.fit_transform(df)
plt.figure()
plt.plot(np.cumsum(pca.explained_variance_ratio_))
plt.xlabel('Number of Components')
plt.ylabel('Variance(%)')
plt.title('Explained Variance')
plt.show()


pca=PCA(n_components=100)
new_data=pca.fit_transform(df)
i=1
for i in range(1,100):
    i=i+1
    print(i)
principal_df=pd.DataFrame(data=new_data,columns=print(i))


print(np.cumsum(pca.explained_variance_ratio_))

[0.13703072 0.19827163 0.25539076 0.29448893 0.3291062  0.36142485
 0.39144063 0.41963488 0.44715696 0.47190124 0.4937025  0.51512512
 0.53499643 0.55411458 0.57226237 0.58997943 0.60411718 0.61775697
 0.63034134 0.64249376 0.65441404 0.66541721 0.67579626 0.68574853
 0.69521506 0.70411474 0.71294788 0.721705   0.73027523 0.7382594
 0.74620079 0.75394911 0.76161212 0.76902063 0.7762017  0.78308656
 0.7897872  0.79638021 0.80295271 0.80948365 0.81598063 0.82245577
 0.82875674 0.83488919 0.84061445 0.84627447 0.85161969 0.85676582
 0.86170511 0.86646483 0.87118848 0.87581601 0.88037229 0.88478778
 0.88906676 0.89315644 0.89711854 0.90097744 0.90469099 0.90829636
 0.91179795 0.91511401 0.91816486 0.9210018  0.92378782 0.9263941
 0.92893867 0.93139733 0.93384103 0.93625241 0.93845657 0.94054386
 0.9426014  0.94457709 0.94645363 0.94829237 0.9500309  0.95168446
 0.95325096 0.95480117 0.95634487 0.95772624 0.95908233 0.96033498
 0.96154759 0.96271282 0.96387123 0.96501777 0.96607519 0.96711017
 0.96811333 0.96908436 0.97003736 0.97098791 0.97190339 0.97280466
 0.97365512 0.97447107 0.97527222 0.97605349]


principal_df


principal_df.corr()


plt.figure(figsize=(90,50))
sns.heatmap(principal_df.corr(),annot=True,cmap='viridis')

<AxesSubplot: >


x=app_bure_prev.drop(['TARGET','SK_ID_CURR'],axis=1)
x


y=app_bure_prev.TARGET
y

0         1
1         0
2         0
3         0
4         0
         ..
307506    0
307507    0
307508    0
307509    1
307510    0
Name: TARGET, Length: 304531, dtype: int64


## preparing training and testing data
from sklearn.model_selection import train_test_split

x_train_, x_test_, y_train_, y_test_ = train_test_split(x, y, test_size=0.30, random_state=42)


from sklearn.metrics import accuracy_score, confusion_matrix,precision_score,recall_score,f1_score,classification_report


from sklearn.linear_model import LogisticRegression
LR=LogisticRegression()
LR.fit(x_train,y_train)

LogisticRegression()

LogisticRegression()


y_hat_test=LR.predict(x_test)
y_hat_test

array([0, 0, 0, ..., 0, 0, 0], dtype=int64)


acc=accuracy_score(y_test,y_hat_test)
acc

0.9188131296546832


print(classification_report(y_test,y_hat_test))

              precision    recall  f1-score   support

           0       0.92      1.00      0.96     69975
           1       0.19      0.00      0.00      6158

    accuracy                           0.92     76133
   macro avg       0.55      0.50      0.48     76133
weighted avg       0.86      0.92      0.88     76133


y_hat_train=LR.predict(x_train)
y_hat_train

array([0, 0, 0, ..., 0, 0, 0], dtype=int64)


acc=accuracy_score(y_train,y_hat_train)
acc

0.9187120727852258


print(classification_report(y_train,y_hat_train))

              precision    recall  f1-score   support

           0       0.92      1.00      0.96    209889
           1       0.19      0.00      0.00     18509

    accuracy                           0.92    228398
   macro avg       0.56      0.50      0.48    228398
weighted avg       0.86      0.92      0.88    228398


from imblearn.over_sampling import SMOTE
sm=SMOTE()
x_sm,y_sm=sm.fit_resample(x_train,y_train)
x_sm1,y_sm1=sm.fit_resample(x_test,y_test)


from collections import Counter
print(Counter(y_test))
print(Counter(y_sm1))

Counter({0: 69975, 1: 6158})
Counter({1: 69975, 0: 69975})


from collections import Counter
print(Counter(y_train))
print(Counter(y_sm))

Counter({0: 209889, 1: 18509})
Counter({0: 209889, 1: 209889})


from sklearn.linear_model import LogisticRegression
LR=LogisticRegression()
LR.fit(x_sm,y_sm)

LogisticRegression()

LogisticRegression()


y_sm_test=LR.predict(x_sm1)
y_sm_test

array([0, 1, 0, ..., 1, 1, 1], dtype=int64)


acc=accuracy_score(y_sm1,y_sm_test)
acc

0.6238585209003216


print(classification_report(y_sm1,y_sm_test))

              precision    recall  f1-score   support

           0       0.63      0.60      0.61     69975
           1       0.62      0.65      0.63     69975

    accuracy                           0.62    139950
   macro avg       0.62      0.62      0.62    139950
weighted avg       0.62      0.62      0.62    139950


y_sm_train=LR.predict(x_sm)
y_sm_train

array([0, 1, 1, ..., 0, 0, 1], dtype=int64)


acc=accuracy_score(y_sm,y_sm_train)
acc

0.6198847962494461


print(classification_report(y_sm,y_sm_train))

              precision    recall  f1-score   support

           0       0.62      0.60      0.61    209889
           1       0.62      0.64      0.63    209889

    accuracy                           0.62    419778
   macro avg       0.62      0.62      0.62    419778
weighted avg       0.62      0.62      0.62    419778


from sklearn.tree import DecisionTreeClassifier#importing decision tree from sklearn.tree
dt=DecisionTreeClassifier()                 #object creation for decision tree  
dt.fit(x_train,y_train)       #training the model

DecisionTreeClassifier()

DecisionTreeClassifier()


y_hat_test1=dt.predict(x_test)#prediction
y_hat_test1#predicted values

array([1, 0, 0, ..., 1, 0, 0], dtype=int64)


acc=accuracy_score(y_test,y_hat_test1)
acc

0.8536902525842933


print(classification_report(y_test,y_hat_test))

              precision    recall  f1-score   support

           0       0.92      1.00      0.96     69975
           1       0.19      0.00      0.00      6158

    accuracy                           0.92     76133
   macro avg       0.55      0.50      0.48     76133
weighted avg       0.86      0.92      0.88     76133


y_hat_train1=dt.predict(x_train)
y_hat_train1

array([0, 0, 0, ..., 0, 0, 0], dtype=int64)


acc=accuracy_score(y_train,y_hat_train)
acc

0.9187120727852258


print(classification_report(y_train,y_hat_train1))

              precision    recall  f1-score   support

           0       1.00      1.00      1.00    209889
           1       1.00      1.00      1.00     18509

    accuracy                           1.00    228398
   macro avg       1.00      1.00      1.00    228398
weighted avg       1.00      1.00      1.00    228398


from sklearn.tree import DecisionTreeClassifier#importing decision tree from sklearn.tree
dt=DecisionTreeClassifier()                 #object creation for decision tree  
dt.fit(x_sm,y_sm)       #training the model

DecisionTreeClassifier()

DecisionTreeClassifier()


y_sm_test1=dt.predict(x_sm1)
y_sm_test1

array([0, 0, 0, ..., 1, 1, 1], dtype=int64)


acc=accuracy_score(y_sm1,y_sm_test1)
acc

0.8546052161486245


print(classification_report(y_sm1,y_sm_test1))

              precision    recall  f1-score   support

           0       0.84      0.88      0.86     69975
           1       0.88      0.83      0.85     69975

    accuracy                           0.85    139950
   macro avg       0.86      0.85      0.85    139950
weighted avg       0.86      0.85      0.85    139950


y_sm_train1=dt.predict(x_sm)
y_sm_train1

array([0, 0, 0, ..., 1, 1, 1], dtype=int64)


acc=accuracy_score(y_sm,y_sm_train1)
acc

1.0


print(classification_report(y_sm,y_sm_train1))

              precision    recall  f1-score   support

           0       1.00      1.00      1.00    209889
           1       1.00      1.00      1.00    209889

    accuracy                           1.00    419778
   macro avg       1.00      1.00      1.00    419778
weighted avg       1.00      1.00      1.00    419778


from sklearn.ensemble import RandomForestClassifier    #importing randomforest

rf= RandomForestClassifier()#object creation ,taking 100 decision tree in random forest 
rf.fit(x_train,y_train)#training the data

RandomForestClassifier()

RandomForestClassifier()


y_predict_test=rf.predict(x_test)#testing
y_predict_test

array([0, 0, 0, ..., 0, 0, 0], dtype=int64)


acc=accuracy_score(y_test,y_predict_test)
acc

0.9191809070967911


print(classification_report(y_test,y_predict_test))

              precision    recall  f1-score   support

           0       0.92      1.00      0.96     69975
           1       1.00      0.00      0.00      6158

    accuracy                           0.92     76133
   macro avg       0.96      0.50      0.48     76133
weighted avg       0.93      0.92      0.88     76133


y_predict_train=rf.predict(x_train)#testing
y_predict_train

array([0, 0, 0, ..., 0, 0, 0], dtype=int64)


acc=accuracy_score(y_train,y_predict_train)
acc

0.9999343251692221


print(classification_report(y_train,y_predict_train))

              precision    recall  f1-score   support

           0       1.00      1.00      1.00    209889
           1       1.00      1.00      1.00     18509

    accuracy                           1.00    228398
   macro avg       1.00      1.00      1.00    228398
weighted avg       1.00      1.00      1.00    228398


from sklearn.ensemble import RandomForestClassifier    #importing randomforest

rf= RandomForestClassifier()#object creation ,taking 100 decision tree in random forest 
rf.fit(x_sm,y_sm)

RandomForestClassifier()

RandomForestClassifier()


y_sm_test2=rf.predict(x_sm1)
y_sm_test2

array([0, 0, 0, ..., 1, 1, 1], dtype=int64)


acc=accuracy_score(y_sm1,y_sm_test2)
acc

0.9267667023937121


print(classification_report(y_sm1,y_sm_test2))

              precision    recall  f1-score   support

           0       0.88      0.99      0.93     69975
           1       0.99      0.86      0.92     69975

    accuracy                           0.93    139950
   macro avg       0.93      0.93      0.93    139950
weighted avg       0.93      0.93      0.93    139950


y_sm_train2=rf.predict(x_sm)
y_sm_train2

array([0, 0, 0, ..., 1, 1, 1], dtype=int64)


acc=accuracy_score(y_sm,y_sm_train2)
acc

1.0


print(classification_report(y_sm,y_sm_train2))

              precision    recall  f1-score   support

           0       1.00      1.00      1.00    209889
           1       1.00      1.00      1.00    209889

    accuracy                           1.00    419778
   macro avg       1.00      1.00      1.00    419778
weighted avg       1.00      1.00      1.00    419778


import xgboost


## model creation
from xgboost import XGBClassifier                          #importing the model library
xgb=XGBClassifier()                           ## object creation
xgb.fit(x_train,y_train)

XGBClassifier(base_score=None, booster=None, callbacks=None,
              colsample_bylevel=None, colsample_bynode=None,
              colsample_bytree=None, early_stopping_rounds=None,
              enable_categorical=False, eval_metric=None, feature_types=None,
              gamma=None, gpu_id=None, grow_policy=None, importance_type=None,
              interaction_constraints=None, learning_rate=None, max_bin=None,
              max_cat_threshold=None, max_cat_to_onehot=None,
              max_delta_step=None, max_depth=None, max_leaves=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=None, ...)

XGBClassifier(base_score=None, booster=None, callbacks=None,
              colsample_bylevel=None, colsample_bynode=None,
              colsample_bytree=None, early_stopping_rounds=None,
              enable_categorical=False, eval_metric=None, feature_types=None,
              gamma=None, gpu_id=None, grow_policy=None, importance_type=None,
              interaction_constraints=None, learning_rate=None, max_bin=None,
              max_cat_threshold=None, max_cat_to_onehot=None,
              max_delta_step=None, max_depth=None, max_leaves=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=None, ...)


y_hat_test2=xgb.predict(x_test) 
y_hat_test2

array([0, 0, 0, ..., 0, 0, 0])


acc=accuracy_score(y_test,y_hat_test2)
acc

0.9185372965731023


print(classification_report(y_test,y_hat_test2))

              precision    recall  f1-score   support

           0       0.92      0.99      0.96     69975
           1       0.47      0.06      0.10      6158

    accuracy                           0.92     76133
   macro avg       0.70      0.53      0.53     76133
weighted avg       0.89      0.92      0.89     76133


y_hat_train2=xgb.predict(x_train)
y_hat_train2

array([0, 0, 0, ..., 0, 0, 0])


acc=accuracy_score(y_train,y_hat_train2)
acc

0.928156113451081


print(classification_report(y_train,y_hat_train2))

              precision    recall  f1-score   support

           0       0.93      1.00      0.96    209889
           1       0.86      0.14      0.23     18509

    accuracy                           0.93    228398
   macro avg       0.89      0.57      0.60    228398
weighted avg       0.92      0.93      0.90    228398


from xgboost import XGBClassifier                          #importing the model library
xgb=XGBClassifier()                           ## object creation
xgb.fit(x_sm,y_sm)

XGBClassifier(base_score=None, booster=None, callbacks=None,
              colsample_bylevel=None, colsample_bynode=None,
              colsample_bytree=None, early_stopping_rounds=None,
              enable_categorical=False, eval_metric=None, feature_types=None,
              gamma=None, gpu_id=None, grow_policy=None, importance_type=None,
              interaction_constraints=None, learning_rate=None, max_bin=None,
              max_cat_threshold=None, max_cat_to_onehot=None,
              max_delta_step=None, max_depth=None, max_leaves=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=None, ...)

XGBClassifier(base_score=None, booster=None, callbacks=None,
              colsample_bylevel=None, colsample_bynode=None,
              colsample_bytree=None, early_stopping_rounds=None,
              enable_categorical=False, eval_metric=None, feature_types=None,
              gamma=None, gpu_id=None, grow_policy=None, importance_type=None,
              interaction_constraints=None, learning_rate=None, max_bin=None,
              max_cat_threshold=None, max_cat_to_onehot=None,
              max_delta_step=None, max_depth=None, max_leaves=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, num_parallel_tree=None,
              predictor=None, random_state=None, ...)


y_sm_test4=xgb.predict(x_sm1)
y_sm_test4

array([0, 0, 0, ..., 1, 1, 1])


acc=accuracy_score(y_sm1,y_sm_test4)
acc

0.954076455877099


print(classification_report(y_sm1,y_sm_test4))

              precision    recall  f1-score   support

           0       0.92      0.99      0.96     69975
           1       0.99      0.92      0.95     69975

    accuracy                           0.95    139950
   macro avg       0.96      0.95      0.95    139950
weighted avg       0.96      0.95      0.95    139950


y_sm_train4=xgb.predict(x_sm)
y_sm_train4

array([0, 0, 0, ..., 1, 1, 1])


acc=accuracy_score(y_sm,y_sm_train4)
acc

0.9592618002849125


print(classification_report(y_sm,y_sm_train4))

              precision    recall  f1-score   support

           0       0.93      1.00      0.96    209889
           1       1.00      0.92      0.96    209889

    accuracy                           0.96    419778
   macro avg       0.96      0.96      0.96    419778
weighted avg       0.96      0.96      0.96    419778

	SK_ID_CURR	TARGET	CNT_CHILDREN	AMT_INCOME_TOTAL	AMT_CREDIT	AMT_ANNUITY	AMT_GOODS_PRICE	REGION_POPULATION_RELATIVE	DAYS_BIRTH	DAYS_EMPLOYED	...	FLAG_DOCUMENT_18	FLAG_DOCUMENT_19	FLAG_DOCUMENT_20	FLAG_DOCUMENT_21	AMT_REQ_CREDIT_BUREAU_HOUR	AMT_REQ_CREDIT_BUREAU_DAY	AMT_REQ_CREDIT_BUREAU_WEEK	AMT_REQ_CREDIT_BUREAU_MON	AMT_REQ_CREDIT_BUREAU_QRT	AMT_REQ_CREDIT_BUREAU_YEAR
count	307511.000000	307511.000000	307511.000000	3.075110e+05	3.075110e+05	307499.000000	3.072330e+05	307511.000000	307511.000000	307511.000000	...	307511.000000	307511.000000	307511.000000	307511.000000	265992.000000	265992.000000	265992.000000	265992.000000	265992.000000	265992.000000
mean	278180.518577	0.080729	0.417052	1.687979e+05	5.990260e+05	27108.573909	5.383962e+05	0.020868	-16036.995067	63815.045904	...	0.008130	0.000595	0.000507	0.000335	0.006402	0.007000	0.034362	0.267395	0.265474	1.899974
std	102790.175348	0.272419	0.722121	2.371231e+05	4.024908e+05	14493.737315	3.694465e+05	0.013831	4363.988632	141275.766519	...	0.089798	0.024387	0.022518	0.018299	0.083849	0.110757	0.204685	0.916002	0.794056	1.869295
min	100002.000000	0.000000	0.000000	2.565000e+04	4.500000e+04	1615.500000	4.050000e+04	0.000290	-25229.000000	-17912.000000	...	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
25%	189145.500000	0.000000	0.000000	1.125000e+05	2.700000e+05	16524.000000	2.385000e+05	0.010006	-19682.000000	-2760.000000	...	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
50%	278202.000000	0.000000	0.000000	1.471500e+05	5.135310e+05	24903.000000	4.500000e+05	0.018850	-15750.000000	-1213.000000	...	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	1.000000
75%	367142.500000	0.000000	1.000000	2.025000e+05	8.086500e+05	34596.000000	6.795000e+05	0.028663	-12413.000000	-289.000000	...	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	3.000000
max	456255.000000	1.000000	19.000000	1.170000e+08	4.050000e+06	258025.500000	4.050000e+06	0.072508	-7489.000000	365243.000000	...	1.000000	1.000000	1.000000	1.000000	4.000000	9.000000	8.000000	27.000000	261.000000	25.000000

	SK_ID_PREV	SK_ID_CURR	MONTHS_BALANCE	CNT_INSTALMENT	CNT_INSTALMENT_FUTURE	NAME_CONTRACT_STATUS
0	1803195	182943	-31	48.0	45.0	Active
1	1715348	367990	-33	36.0	35.0	Active
2	1784872	397406	-32	12.0	9.0	Active
3	1903291	269225	-35	48.0	42.0	Active
4	2341044	334279	-35	36.0	35.0	Active

	SK_ID_PREV	SK_ID_CURR	MONTHS_BALANCE	CNT_INSTALMENT	CNT_INSTALMENT_FUTURE	SK_DPD	SK_DPD_DEF
count	1.000136e+07	1.000136e+07	1.000136e+07	9.975287e+06	9.975271e+06	1.000136e+07	1.000136e+07
mean	1.903217e+06	2.784039e+05	-3.501259e+01	1.708965e+01	1.048384e+01	1.160693e+01	6.544684e-01
std	5.358465e+05	1.027637e+05	2.606657e+01	1.199506e+01	1.110906e+01	1.327140e+02	3.276249e+01
min	1.000001e+06	1.000010e+05	-9.600000e+01	1.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00
25%	1.434405e+06	1.895500e+05	-5.400000e+01	1.000000e+01	3.000000e+00	0.000000e+00	0.000000e+00
50%	1.896565e+06	2.786540e+05	-2.800000e+01	1.200000e+01	7.000000e+00	0.000000e+00	0.000000e+00
75%	2.368963e+06	3.674290e+05	-1.300000e+01	2.400000e+01	1.400000e+01	0.000000e+00	0.000000e+00
max	2.843499e+06	4.562550e+05	-1.000000e+00	9.200000e+01	8.500000e+01	4.231000e+03	3.595000e+03

	SK_ID_BUREAU	MONTHS_BALANCE	STATUS
0	5715448	0	C
1	5715448	-1	C
2	5715448	-2	C
3	5715448	-3	C
4	5715448	-4	C

	SK_ID_BUREAU	MONTHS_BALANCE
count	2.729992e+07	2.729992e+07
mean	6.036297e+06	-3.074169e+01
std	4.923489e+05	2.386451e+01
min	5.001709e+06	-9.600000e+01
25%	5.730933e+06	-4.600000e+01
50%	6.070821e+06	-2.500000e+01
75%	6.431951e+06	-1.100000e+01
max	6.842888e+06	0.000000e+00

	SK_ID_CURR	TARGET	NAME_CONTRACT_TYPE	CODE_GENDER	FLAG_OWN_CAR	FLAG_OWN_REALTY	AMT_INCOME_TOTAL	AMT_CREDIT	AMT_ANNUITY	...	AMT_REQ_CREDIT_BUREAU_HOUR	AMT_REQ_CREDIT_BUREAU_DAY	AMT_REQ_CREDIT_BUREAU_WEEK	AMT_REQ_CREDIT_BUREAU_MON	AMT_REQ_CREDIT_BUREAU_QRT	AMT_REQ_CREDIT_BUREAU_YEAR
0	100002	1	Cash loans	M	N	Y	202500.0	406597.5	24700.5	...	0.0	0.0	0.0	0.0	0.0	1.0
1	100003	0	Cash loans	F	N	N	270000.0	1293502.5	35698.5	...	0.0	0.0	0.0	0.0	0.0	0.0
2	100004	0	Revolving loans	M	Y	Y	67500.0	135000.0	6750.0	...	0.0	0.0	0.0	0.0	0.0	0.0
3	100006	0	Cash loans	F	N	Y	135000.0	312682.5	29686.5	...	NaN	NaN	NaN	NaN	NaN	NaN
4	100007	0	Cash loans	M	N	Y	121500.0	513000.0	21865.5	...	0.0	0.0	0.0	0.0	0.0	0.0

	SK_ID_PREV	SK_ID_CURR	NAME_CONTRACT_TYPE	AMT_ANNUITY	AMT_APPLICATION	AMT_CREDIT	AMT_DOWN_PAYMENT	AMT_GOODS_PRICE	WEEKDAY_APPR_PROCESS_START	HOUR_APPR_PROCESS_START	...	NAME_SELLER_INDUSTRY	CNT_PAYMENT	NAME_YIELD_GROUP	PRODUCT_COMBINATION	DAYS_FIRST_DRAWING	DAYS_FIRST_DUE	DAYS_LAST_DUE_1ST_VERSION	DAYS_LAST_DUE	DAYS_TERMINATION	NFLAG_INSURED_ON_APPROVAL
0	2030495	271877	Consumer loans	1730.430	17145.0	17145.0	0.0	17145.0	SATURDAY	15	...	Connectivity	12.0	middle	POS mobile with interest	365243.0	-42.0	300.0	-42.0	-37.0	0.0
1	2802425	108129	Cash loans	25188.615	607500.0	679671.0	NaN	607500.0	THURSDAY	11	...	XNA	36.0	low_action	Cash X-Sell: low	365243.0	-134.0	916.0	365243.0	365243.0	1.0
2	2523466	122040	Cash loans	15060.735	112500.0	136444.5	NaN	112500.0	TUESDAY	11	...	XNA	12.0	high	Cash X-Sell: high	365243.0	-271.0	59.0	365243.0	365243.0	1.0
3	2819243	176158	Cash loans	47041.335	450000.0	470790.0	NaN	450000.0	MONDAY	7	...	XNA	12.0	middle	Cash X-Sell: middle	365243.0	-482.0	-152.0	-182.0	-177.0	1.0
4	1784265	202054	Cash loans	31924.395	337500.0	404055.0	NaN	337500.0	THURSDAY	9	...	XNA	24.0	high	Cash Street: high	NaN	NaN	NaN	NaN	NaN	NaN

	SK_ID_PREV	SK_ID_CURR	AMT_ANNUITY	AMT_APPLICATION	AMT_CREDIT	AMT_DOWN_PAYMENT	AMT_GOODS_PRICE	HOUR_APPR_PROCESS_START	NFLAG_LAST_APPL_IN_DAY	RATE_DOWN_PAYMENT	...	RATE_INTEREST_PRIVILEGED	DAYS_DECISION	SELLERPLACE_AREA	CNT_PAYMENT	DAYS_FIRST_DRAWING	DAYS_FIRST_DUE	DAYS_LAST_DUE_1ST_VERSION	DAYS_LAST_DUE	DAYS_TERMINATION	NFLAG_INSURED_ON_APPROVAL
count	1.670214e+06	1.670214e+06	1.297979e+06	1.670214e+06	1.670213e+06	7.743700e+05	1.284699e+06	1.670214e+06	1.670214e+06	774370.000000	...	5951.000000	1.670214e+06	1.670214e+06	1.297984e+06	997149.000000	997149.000000	997149.000000	997149.000000	997149.000000	997149.000000
mean	1.923089e+06	2.783572e+05	1.595512e+04	1.752339e+05	1.961140e+05	6.697402e+03	2.278473e+05	1.248418e+01	9.964675e-01	0.079637	...	0.773503	-8.806797e+02	3.139511e+02	1.605408e+01	342209.855039	13826.269337	33767.774054	76582.403064	81992.343838	0.332570
std	5.325980e+05	1.028148e+05	1.478214e+04	2.927798e+05	3.185746e+05	2.092150e+04	3.153966e+05	3.334028e+00	5.932963e-02	0.107823	...	0.100879	7.790997e+02	7.127443e+03	1.456729e+01	88916.115834	72444.869708	106857.034789	149647.415123	153303.516729	0.471134
min	1.000001e+06	1.000010e+05	0.000000e+00	0.000000e+00	0.000000e+00	-9.000000e-01	0.000000e+00	0.000000e+00	0.000000e+00	-0.000015	...	0.373150	-2.922000e+03	-1.000000e+00	0.000000e+00	-2922.000000	-2892.000000	-2801.000000	-2889.000000	-2874.000000	0.000000
25%	1.461857e+06	1.893290e+05	6.321780e+03	1.872000e+04	2.416050e+04	0.000000e+00	5.084100e+04	1.000000e+01	1.000000e+00	0.000000	...	0.715645	-1.300000e+03	-1.000000e+00	6.000000e+00	365243.000000	-1628.000000	-1242.000000	-1314.000000	-1270.000000	0.000000
50%	1.923110e+06	2.787145e+05	1.125000e+04	7.104600e+04	8.054100e+04	1.638000e+03	1.123200e+05	1.200000e+01	1.000000e+00	0.051605	...	0.835095	-5.810000e+02	3.000000e+00	1.200000e+01	365243.000000	-831.000000	-361.000000	-537.000000	-499.000000	0.000000
75%	2.384280e+06	3.675140e+05	2.065842e+04	1.803600e+05	2.164185e+05	7.740000e+03	2.340000e+05	1.500000e+01	1.000000e+00	0.108909	...	0.852537	-2.800000e+02	8.200000e+01	2.400000e+01	365243.000000	-411.000000	129.000000	-74.000000	-44.000000	1.000000
max	2.845382e+06	4.562550e+05	4.180581e+05	6.905160e+06	6.905160e+06	3.060045e+06	6.905160e+06	2.300000e+01	1.000000e+00	1.000000	...	1.000000	-1.000000e+00	4.000000e+06	8.400000e+01	365243.000000	365243.000000	365243.000000	365243.000000	365243.000000	1.000000

	SK_ID_PREV	SK_ID_CURR	MONTHS_BALANCE	AMT_BALANCE	AMT_CREDIT_LIMIT_ACTUAL	AMT_DRAWINGS_ATM_CURRENT	AMT_DRAWINGS_CURRENT	AMT_DRAWINGS_POS_CURRENT	AMT_INST_MIN_REGULARITY	...	AMT_RECIVABLE	AMT_TOTAL_RECEIVABLE	CNT_DRAWINGS_ATM_CURRENT	CNT_DRAWINGS_CURRENT	CNT_DRAWINGS_POS_CURRENT	CNT_INSTALMENT_MATURE_CUM	NAME_CONTRACT_STATUS
0	2562384	378907	-6	56.970	135000	0.0	877.5	877.5	1700.325	...	0.000	0.000	0.0	1	1.0	35.0	Active
1	2582071	363914	-1	63975.555	45000	2250.0	2250.0	0.0	2250.000	...	64875.555	64875.555	1.0	1	0.0	69.0	Active
2	1740877	371185	-7	31815.225	450000	0.0	0.0	0.0	2250.000	...	31460.085	31460.085	0.0	0	0.0	30.0	Active
3	1389973	337855	-4	236572.110	225000	2250.0	2250.0	0.0	11795.760	...	233048.970	233048.970	1.0	1	0.0	10.0	Active
4	1891521	126868	-1	453919.455	450000	0.0	11547.0	11547.0	22924.890	...	453919.455	453919.455	0.0	1	1.0	101.0	Active

	SK_ID_PREV	SK_ID_CURR	MONTHS_BALANCE	AMT_BALANCE	AMT_CREDIT_LIMIT_ACTUAL	AMT_DRAWINGS_ATM_CURRENT	AMT_DRAWINGS_CURRENT	AMT_DRAWINGS_OTHER_CURRENT	AMT_DRAWINGS_POS_CURRENT	AMT_INST_MIN_REGULARITY	...	AMT_RECEIVABLE_PRINCIPAL	AMT_RECIVABLE	AMT_TOTAL_RECEIVABLE	CNT_DRAWINGS_ATM_CURRENT	CNT_DRAWINGS_CURRENT	CNT_DRAWINGS_OTHER_CURRENT	CNT_DRAWINGS_POS_CURRENT	CNT_INSTALMENT_MATURE_CUM	SK_DPD	SK_DPD_DEF
count	3.840312e+06	3.840312e+06	3.840312e+06	3.840312e+06	3.840312e+06	3.090496e+06	3.840312e+06	3.090496e+06	3.090496e+06	3.535076e+06	...	3.840312e+06	3.840312e+06	3.840312e+06	3.090496e+06	3.840312e+06	3.090496e+06	3.090496e+06	3.535076e+06	3.840312e+06	3.840312e+06
mean	1.904504e+06	2.783242e+05	-3.452192e+01	5.830016e+04	1.538080e+05	5.961325e+03	7.433388e+03	2.881696e+02	2.968805e+03	3.540204e+03	...	5.596588e+04	5.808881e+04	5.809829e+04	3.094490e-01	7.031439e-01	4.812496e-03	5.594791e-01	2.082508e+01	9.283667e+00	3.316220e-01
std	5.364695e+05	1.027045e+05	2.666775e+01	1.063070e+05	1.651457e+05	2.822569e+04	3.384608e+04	8.201989e+03	2.079689e+04	5.600154e+03	...	1.025336e+05	1.059654e+05	1.059718e+05	1.100401e+00	3.190347e+00	8.263861e-02	3.240649e+00	2.005149e+01	9.751570e+01	2.147923e+01
min	1.000018e+06	1.000060e+05	-9.600000e+01	-4.202502e+05	0.000000e+00	-6.827310e+03	-6.211620e+03	0.000000e+00	0.000000e+00	0.000000e+00	...	-4.233058e+05	-4.202502e+05	-4.202502e+05	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00
25%	1.434385e+06	1.895170e+05	-5.500000e+01	0.000000e+00	4.500000e+04	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	...	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	4.000000e+00	0.000000e+00	0.000000e+00
50%	1.897122e+06	2.783960e+05	-2.800000e+01	0.000000e+00	1.125000e+05	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	...	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	1.500000e+01	0.000000e+00	0.000000e+00
75%	2.369328e+06	3.675800e+05	-1.100000e+01	8.904669e+04	1.800000e+05	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	6.633911e+03	...	8.535924e+04	8.889949e+04	8.891451e+04	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	3.200000e+01	0.000000e+00	0.000000e+00
max	2.843496e+06	4.562500e+05	-1.000000e+00	1.505902e+06	1.350000e+06	2.115000e+06	2.287098e+06	1.529847e+06	2.239274e+06	2.028820e+05	...	1.472317e+06	1.493338e+06	1.493338e+06	5.100000e+01	1.650000e+02	1.200000e+01	1.650000e+02	1.200000e+02	3.260000e+03	3.260000e+03

	SK_ID_CURR	SK_ID_BUREAU	CREDIT_ACTIVE	CREDIT_CURRENCY	DAYS_CREDIT	DAYS_CREDIT_ENDDATE	DAYS_ENDDATE_FACT	AMT_CREDIT_MAX_OVERDUE	AMT_CREDIT_SUM	AMT_CREDIT_SUM_DEBT	AMT_CREDIT_SUM_LIMIT	CREDIT_TYPE	DAYS_CREDIT_UPDATE	AMT_ANNUITY
0	215354	5714462	Closed	currency 1	-497	-153.0	-153.0	NaN	91323.0	0.0	NaN	Consumer credit	-131	NaN
1	215354	5714463	Active	currency 1	-208	1075.0	NaN	NaN	225000.0	171342.0	NaN	Credit card	-20	NaN
2	215354	5714464	Active	currency 1	-203	528.0	NaN	NaN	464323.5	NaN	NaN	Consumer credit	-16	NaN
3	215354	5714465	Active	currency 1	-203	NaN	NaN	NaN	90000.0	NaN	NaN	Credit card	-16	NaN
4	215354	5714466	Active	currency 1	-629	1197.0	NaN	77674.5	2700000.0	NaN	NaN	Consumer credit	-21	NaN

	SK_ID_CURR	SK_ID_BUREAU	DAYS_CREDIT	CREDIT_DAY_OVERDUE	DAYS_CREDIT_ENDDATE	DAYS_ENDDATE_FACT	AMT_CREDIT_MAX_OVERDUE	CNT_CREDIT_PROLONG	AMT_CREDIT_SUM	AMT_CREDIT_SUM_DEBT	AMT_CREDIT_SUM_LIMIT	AMT_CREDIT_SUM_OVERDUE	DAYS_CREDIT_UPDATE	AMT_ANNUITY
count	1.716428e+06	1.716428e+06	1.716428e+06	1.716428e+06	1.610875e+06	1.082775e+06	5.919400e+05	1.716428e+06	1.716415e+06	1.458759e+06	1.124648e+06	1.716428e+06	1.716428e+06	4.896370e+05
mean	2.782149e+05	5.924434e+06	-1.142108e+03	8.181666e-01	5.105174e+02	-1.017437e+03	3.825418e+03	6.410406e-03	3.549946e+05	1.370851e+05	6.229515e+03	3.791276e+01	-5.937483e+02	1.571276e+04
std	1.029386e+05	5.322657e+05	7.951649e+02	3.654443e+01	4.994220e+03	7.140106e+02	2.060316e+05	9.622391e-02	1.149811e+06	6.774011e+05	4.503203e+04	5.937650e+03	7.207473e+02	3.258269e+05
min	1.000010e+05	5.000000e+06	-2.922000e+03	0.000000e+00	-4.206000e+04	-4.202300e+04	0.000000e+00	0.000000e+00	0.000000e+00	-4.705600e+06	-5.864061e+05	0.000000e+00	-4.194700e+04	0.000000e+00
25%	1.888668e+05	5.463954e+06	-1.666000e+03	0.000000e+00	-1.138000e+03	-1.489000e+03	0.000000e+00	0.000000e+00	5.130000e+04	0.000000e+00	0.000000e+00	0.000000e+00	-9.080000e+02	0.000000e+00
50%	2.780550e+05	5.926304e+06	-9.870000e+02	0.000000e+00	-3.300000e+02	-8.970000e+02	0.000000e+00	0.000000e+00	1.255185e+05	0.000000e+00	0.000000e+00	0.000000e+00	-3.950000e+02	0.000000e+00
75%	3.674260e+05	6.385681e+06	-4.740000e+02	0.000000e+00	4.740000e+02	-4.250000e+02	0.000000e+00	0.000000e+00	3.150000e+05	4.015350e+04	0.000000e+00	0.000000e+00	-3.300000e+01	1.350000e+04
max	4.562550e+05	6.843457e+06	0.000000e+00	2.792000e+03	3.119900e+04	0.000000e+00	1.159872e+08	9.000000e+00	5.850000e+08	1.701000e+08	4.705600e+06	3.756681e+06	3.720000e+02	1.184534e+08

	Total	Percent
COMMONAREA_MEDI	214865	69.872297
COMMONAREA_AVG	214865	69.872297
COMMONAREA_MODE	214865	69.872297
NONLIVINGAPARTMENTS_MODE	213514	69.432963
NONLIVINGAPARTMENTS_AVG	213514	69.432963
NONLIVINGAPARTMENTS_MEDI	213514	69.432963
FONDKAPREMONT_MODE	210295	68.386172
LIVINGAPARTMENTS_MODE	210199	68.354953
LIVINGAPARTMENTS_AVG	210199	68.354953
LIVINGAPARTMENTS_MEDI	210199	68.354953
FLOORSMIN_AVG	208642	67.848630
FLOORSMIN_MODE	208642	67.848630
FLOORSMIN_MEDI	208642	67.848630
YEARS_BUILD_MEDI	204488	66.497784
YEARS_BUILD_MODE	204488	66.497784
YEARS_BUILD_AVG	204488	66.497784
OWN_CAR_AGE	202929	65.990810
LANDAREA_MEDI	182590	59.376738
LANDAREA_MODE	182590	59.376738
LANDAREA_AVG	182590	59.376738

	Total	Percent
CNT_INSTALMENT_FUTURE	26087	0.260835
CNT_INSTALMENT	26071	0.260675
SK_ID_PREV	0	0.000000

	Total	Percent
RATE_INTEREST_PRIVILEGED	1664263	99.643698
RATE_INTEREST_PRIMARY	1664263	99.643698
AMT_DOWN_PAYMENT	895844	53.636480
RATE_DOWN_PAYMENT	895844	53.636480
NAME_TYPE_SUITE	820405	49.119754
NFLAG_INSURED_ON_APPROVAL	673065	40.298129
DAYS_TERMINATION	673065	40.298129
DAYS_LAST_DUE	673065	40.298129
DAYS_LAST_DUE_1ST_VERSION	673065	40.298129
DAYS_FIRST_DUE	673065	40.298129
DAYS_FIRST_DRAWING	673065	40.298129
AMT_GOODS_PRICE	385515	23.081773
AMT_ANNUITY	372235	22.286665
CNT_PAYMENT	372230	22.286366
PRODUCT_COMBINATION	346	0.020716
AMT_CREDIT	1	0.000060
NAME_YIELD_GROUP	0	0.000000
NAME_PORTFOLIO	0	0.000000
NAME_SELLER_INDUSTRY	0	0.000000
SELLERPLACE_AREA	0	0.000000

	Total	Percent
DAYS_ENTRY_PAYMENT	2905	0.021352
AMT_PAYMENT	2905	0.021352
SK_ID_PREV	0	0.000000

	Total	Percent
AMT_PAYMENT_CURRENT	767988	19.998063
AMT_DRAWINGS_ATM_CURRENT	749816	19.524872
CNT_DRAWINGS_POS_CURRENT	749816	19.524872
AMT_DRAWINGS_OTHER_CURRENT	749816	19.524872
AMT_DRAWINGS_POS_CURRENT	749816	19.524872
CNT_DRAWINGS_OTHER_CURRENT	749816	19.524872
CNT_DRAWINGS_ATM_CURRENT	749816	19.524872
CNT_INSTALMENT_MATURE_CUM	305236	7.948208
AMT_INST_MIN_REGULARITY	305236	7.948208
SK_ID_PREV	0	0.000000

	Total	Percent
AMT_ANNUITY	1226791	71.473490
AMT_CREDIT_MAX_OVERDUE	1124488	65.513264
DAYS_ENDDATE_FACT	633653	36.916958
AMT_CREDIT_SUM_LIMIT	591780	34.477415
AMT_CREDIT_SUM_DEBT	257669	15.011932
DAYS_CREDIT_ENDDATE	105553	6.149573
AMT_CREDIT_SUM	13	0.000757
CREDIT_ACTIVE	0	0.000000

	0	1	2	3	4	5	6	7	8	9	...	90	91	92	93	94	95	96	97	98	99
0	-1.069993	0.182752	0.224762	0.466566	-0.296921	-0.295750	-0.463716	-0.513895	-0.529139	0.842591	...	0.124051	-0.185508	-0.460209	-0.058217	-0.218401	0.101643	-0.099580	0.007500	0.033038	-0.292569
1	-0.232059	-0.290004	-0.151789	-0.541143	-0.104399	-0.504114	-0.850435	0.448569	-0.018879	0.404731	...	-0.020579	-0.024259	0.078055	-0.069768	0.013315	0.024694	-0.080420	-0.023699	0.042591	-0.012710
2	-1.577270	0.033349	0.153514	-0.562490	0.071476	-0.089890	0.600636	0.423613	-0.550142	1.043077	...	0.070635	-0.041994	-0.077366	-0.014778	0.030544	0.072083	0.017788	0.133722	-0.194084	0.007447
3	1.322030	0.276303	-0.435906	1.175515	0.303640	0.478250	-0.597051	-0.083415	-0.389949	-0.263187	...	0.014922	-0.031021	-0.023674	0.020413	-0.016230	-0.016487	0.033022	0.024404	-0.013820	0.042557
4	0.395797	-0.079751	-0.457191	-0.640798	0.707315	-0.687447	0.779387	-0.091725	0.665795	-0.281248	...	-0.053203	0.069412	0.015410	0.001196	-0.053472	-0.001371	0.001292	-0.042720	0.042988	0.016247
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
304526	-1.729526	0.280461	0.247553	0.000323	1.068703	1.889744	0.228819	0.178182	-0.277107	0.155246	...	-0.009585	0.003983	0.037711	0.010435	-0.060908	-0.033467	-0.033827	-0.123686	-0.002520	-0.065890
304527	-1.446905	-1.583707	0.215260	0.374959	0.461163	0.428501	-1.070779	0.541500	0.672837	-0.298517	...	0.027728	-0.076818	-0.185081	-0.027195	-0.021873	-0.033492	0.001997	0.015269	-0.027229	0.045366
304528	-1.395311	0.298903	-0.774347	-1.096497	0.236309	0.680991	0.180618	-0.927396	0.680844	-0.449020	...	-0.018001	0.016631	0.077625	0.043507	0.111468	0.016865	-0.113705	-0.340958	-0.071870	0.042391
304529	-1.380803	0.119600	-0.547598	0.191041	-0.086738	0.029911	0.415059	-0.914253	0.044289	-0.050822	...	-0.030254	-0.012058	0.036630	-0.015014	-0.016423	-0.071066	-0.016776	-0.083633	0.079677	-0.027230
304530	0.427929	0.787596	-0.399538	-0.822034	0.535917	-0.270132	-0.256005	0.195575	0.892969	1.021583	...	0.004958	0.000542	0.031326	0.024258	-0.083016	-0.018877	0.006587	0.037809	-0.059083	-0.042105

	NAME_CONTRACT_TYPE	CODE_GENDER	FLAG_OWN_CAR	FLAG_OWN_REALTY	CNT_CHILDREN	AMT_INCOME_TOTAL	AMT_CREDIT	AMT_ANNUITY	AMT_GOODS_PRICE	NAME_TYPE_SUITE	...	CREDIT_CNT_INSTALMENT_MATURE_CUM	CREDIT_SK_DPD	CREDIT_SK_DPD_DEF	CREDIT_NAME_CONTRACT_STATUS_Active	CREDIT_NAME_CONTRACT_STATUS_Approved	CREDIT_NAME_CONTRACT_STATUS_Completed	CREDIT_NAME_CONTRACT_STATUS_Demand	CREDIT_NAME_CONTRACT_STATUS_Refused	CREDIT_NAME_CONTRACT_STATUS_Sent proposal	CREDIT_NAME_CONTRACT_STATUS_Signed
51515	0	1	1	1	0	180000.0	1560726.0	43047.0	1395000.0	6	...	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0
240897	0	1	0	1	0	135000.0	640080.0	29970.0	450000.0	6	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
261925	0	0	0	1	2	135000.0	269982.0	29205.0	238500.0	6	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
82413	0	0	1	1	0	157500.0	534141.0	16771.5	441000.0	6	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
214981	0	0	0	1	0	94500.0	116892.0	5580.0	76500.0	6	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
149001	0	0	1	1	0	450000.0	1235587.5	40963.5	1107000.0	6	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
198572	0	1	1	0	0	315000.0	497520.0	39307.5	450000.0	6	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
160464	0	0	0	1	0	112500.0	729792.0	35109.0	630000.0	6	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
226067	1	1	0	1	0	445500.0	427500.0	21375.0	427500.0	6	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
105162	0	0	0	0	0	315000.0	647046.0	17199.0	463500.0	6	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0

	0	1	2	3	4	5	6	7	8	9	...	90	91	92	93	94	95	96	97	98	99
0	1.000000e+00	3.509523e-17	-6.003601e-17	-2.603317e-17	-7.473187e-18	1.808072e-17	4.411952e-17	3.049601e-17	1.951003e-18	-1.012574e-17	...	1.028278e-18	3.432784e-18	5.814233e-17	1.200717e-17	9.977098e-18	-2.770747e-17	6.043889e-18	4.555241e-17	7.089736e-17	1.258585e-17
1	3.509523e-17	1.000000e+00	2.401852e-15	2.967990e-16	2.936291e-16	2.972742e-16	-1.530355e-16	1.050882e-16	5.791542e-17	5.652962e-17	...	3.354229e-18	9.298019e-18	2.204460e-17	1.406786e-17	3.646777e-18	-7.534634e-18	-6.999909e-18	1.804254e-17	2.075264e-18	-1.664701e-17
2	-6.003601e-17	2.401852e-15	1.000000e+00	3.510650e-16	-6.402128e-16	-3.058900e-16	-5.044898e-16	1.289581e-16	1.439599e-16	4.743130e-17	...	-5.845439e-18	-1.180659e-17	-3.034058e-18	-4.614028e-18	-9.276155e-18	-2.366614e-17	1.003848e-18	-4.714906e-18	-1.037746e-17	2.835443e-17
3	-2.603317e-17	2.967990e-16	3.510650e-16	1.000000e+00	1.697816e-15	-6.053957e-16	-1.910533e-15	1.159614e-16	-1.015989e-15	1.470259e-15	...	5.868714e-18	-1.260149e-17	-5.202062e-19	6.967725e-18	-6.657985e-18	4.120928e-18	2.127518e-17	-2.018742e-17	-7.589839e-18	-1.806491e-17
4	-7.473187e-18	2.936291e-16	-6.402128e-16	1.697816e-15	1.000000e+00	1.266313e-15	-1.366309e-15	-5.357198e-16	-3.942660e-17	1.368680e-15	...	1.752911e-17	1.850881e-17	-2.325193e-17	2.027920e-17	6.331575e-18	-1.877933e-17	-1.358344e-17	4.851004e-17	-8.748591e-18	3.858179e-17
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
95	-2.770747e-17	-7.534634e-18	-2.366614e-17	4.120928e-18	-1.877933e-17	-1.556456e-18	1.295660e-17	1.455095e-17	1.773289e-17	-5.201982e-19	...	6.748602e-16	-1.576131e-15	-8.834171e-16	-9.493750e-16	-3.141909e-16	1.000000e+00	-1.569977e-15	-1.765580e-15	1.048564e-15	-1.565231e-15
96	6.043889e-18	-6.999909e-18	1.003848e-18	2.127518e-17	-1.358344e-17	5.438462e-17	-7.428519e-18	-1.588946e-17	-3.398423e-17	1.585808e-17	...	8.638014e-16	-4.000258e-16	1.328441e-17	1.668062e-16	-6.943594e-16	-1.569977e-15	1.000000e+00	4.594176e-16	4.719919e-17	9.476219e-16
97	4.555241e-17	1.804254e-17	-4.714906e-18	-2.018742e-17	4.851004e-17	1.272123e-17	3.673731e-17	5.816711e-18	-1.603250e-17	2.275273e-17	...	2.664862e-15	-4.392981e-17	1.582704e-15	2.162393e-16	-1.269384e-17	-1.765580e-15	4.594176e-16	1.000000e+00	-8.744915e-16	-1.373196e-16
98	7.089736e-17	2.075264e-18	-1.037746e-17	-7.589839e-18	-8.748591e-18	-2.612238e-17	7.165160e-19	2.854139e-17	-4.627516e-18	-7.115592e-19	...	-1.071332e-15	-2.281463e-16	-3.690612e-16	-2.371551e-16	-8.263655e-17	1.048564e-15	4.719919e-17	-8.744915e-16	1.000000e+00	-5.009471e-18
99	1.258585e-17	-1.664701e-17	2.835443e-17	-1.806491e-17	3.858179e-17	1.955428e-17	1.718217e-17	-2.016645e-17	4.436831e-17	1.723623e-17	...	8.597012e-16	8.644199e-16	1.680888e-15	4.899231e-16	1.697981e-16	-1.565231e-15	9.476219e-16	-1.373196e-16	-5.009471e-18	1.000000e+00

Project ID = PRCP-1006-HomeLoanDef¶

Python Implementation : -¶

Business Case:-¶

Domain Analysis : -¶

Current Application:-¶

Previous Application:-¶

Bureau:-¶

Bureau Balance:-¶

Credit Card Balance:-¶

Instalments Payments:-¶

POS Cash:-¶

Application Train¶

POSH CASH BALANCE¶

Bureau Balance¶

previous_application data¶

credit_card_balance data¶

bureau data¶

checking missing data in application_train¶

checking missing data in POS_CASH_balance¶

checking missing data in bureau_balance¶

checking missing data in previous_application¶

checking missing data in installments_payments¶

checking missing data in credit_card_balance¶

checking missing data in bureau¶

EDA( Exploratory Data Analysis)¶

Insights:-¶

Insights:-¶

Insights:-¶

Insights:-¶

Insights:-¶

Distribution of Income sources of Applicants in terms of loan is repayed or not.¶

insights:-¶

Distribution of Education of Applicants in terms of loan is repayed or not¶

insights:-¶

Distribution of Family status of Applicants in terms of loan is repayed or not.¶

Insights:-¶

Data is balanced or imbalanced¶

Insights:-¶

Insights:-¶

Family Status of Applicant's who applied for loan¶

insights:-¶

Income sources of Applicant's who applied for loan¶

Insights:-¶

Education of Applicant's who applied for loan¶

Insights:-¶

For which types of house higher applicant's applied for loan ?¶

Insights:-¶

Occupation of Applicant's who applied for loan¶

Insights:-¶

Types of Organizations who applied for loan¶

Insights:-¶

Contract was approved or not in previous application¶

Insights¶

Payment method that client choose to pay for the previous application¶

Insights:-¶

Handling null values¶

Housing Details:-¶

As all are correlated we can drop these features¶

Converting the Categorical data into Numerical data¶

Using Encoding to Handle the categorical data¶

PCA - Principal Component Analysis¶

Feature Engineering¶

There is no correlation between the features¶

Model Creation¶

Logistic Regression¶

SMOTE¶

Decision Tree¶

Random Forest¶

XGB¶

Conclusion¶

Based on the provided accuracy values for each model, here is the summary:¶

Based on the application of the four models (Logistic Regression, Decision Tree, Random Forest, and XGBoost), here is a summary of the conclusions.¶